diff --git a/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-02-14-09-22.csv b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-02-14-09-22.csv new file mode 100644 index 0000000000000000000000000000000000000000..d5bae2f20a79916c0727e3b8d4b90542cee6934b --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-02-14-09-22.csv @@ -0,0 +1,120 @@ +task,metric,value,err,version +copa,acc,0.74,0.044084400227680794,0 +hendrycksTest-abstract_algebra,acc,0.22,0.04163331998932268,0 +hendrycksTest-abstract_algebra,acc_norm,0.26,0.04408440022768079,0 +hendrycksTest-anatomy,acc,0.28888888888888886,0.03915450630414251,0 +hendrycksTest-anatomy,acc_norm,0.22962962962962963,0.036333844140734636,0 +hendrycksTest-astronomy,acc,0.21710526315789475,0.03355045304882921,0 +hendrycksTest-astronomy,acc_norm,0.3355263157894737,0.03842498559395271,0 +hendrycksTest-business_ethics,acc,0.34,0.04760952285695235,0 +hendrycksTest-business_ethics,acc_norm,0.31,0.04648231987117316,0 +hendrycksTest-clinical_knowledge,acc,0.24528301886792453,0.026480357179895678,0 +hendrycksTest-clinical_knowledge,acc_norm,0.30943396226415093,0.02845015479411863,0 +hendrycksTest-college_biology,acc,0.2152777777777778,0.034370793441061344,0 +hendrycksTest-college_biology,acc_norm,0.2222222222222222,0.034765901043041336,0 +hendrycksTest-college_chemistry,acc,0.26,0.04408440022768078,0 +hendrycksTest-college_chemistry,acc_norm,0.29,0.045604802157206845,0 +hendrycksTest-college_computer_science,acc,0.29,0.04560480215720684,0 +hendrycksTest-college_computer_science,acc_norm,0.24,0.04292346959909284,0 +hendrycksTest-college_mathematics,acc,0.2,0.04020151261036845,0 +hendrycksTest-college_mathematics,acc_norm,0.3,0.046056618647183814,0 +hendrycksTest-college_medicine,acc,0.2543352601156069,0.0332055644308557,0 +hendrycksTest-college_medicine,acc_norm,0.2543352601156069,0.0332055644308557,0 +hendrycksTest-college_physics,acc,0.2549019607843137,0.043364327079931764,0 +hendrycksTest-college_physics,acc_norm,0.28431372549019607,0.04488482852329017,0 +hendrycksTest-computer_security,acc,0.28,0.04512608598542126,0 +hendrycksTest-computer_security,acc_norm,0.36,0.048241815132442176,0 +hendrycksTest-conceptual_physics,acc,0.2553191489361702,0.028504856470514203,0 +hendrycksTest-conceptual_physics,acc_norm,0.1829787234042553,0.025276041000449966,0 +hendrycksTest-econometrics,acc,0.21929824561403508,0.03892431106518753,0 +hendrycksTest-econometrics,acc_norm,0.21929824561403508,0.03892431106518754,0 +hendrycksTest-electrical_engineering,acc,0.2689655172413793,0.036951833116502325,0 +hendrycksTest-electrical_engineering,acc_norm,0.30344827586206896,0.038312260488503336,0 +hendrycksTest-elementary_mathematics,acc,0.21957671957671956,0.02132001859977036,0 +hendrycksTest-elementary_mathematics,acc_norm,0.25925925925925924,0.022569897074918407,0 +hendrycksTest-formal_logic,acc,0.29365079365079366,0.04073524322147127,0 +hendrycksTest-formal_logic,acc_norm,0.23809523809523808,0.038095238095238126,0 +hendrycksTest-global_facts,acc,0.19,0.039427724440366234,0 +hendrycksTest-global_facts,acc_norm,0.2,0.04020151261036846,0 +hendrycksTest-high_school_biology,acc,0.23548387096774193,0.02413763242933771,0 +hendrycksTest-high_school_biology,acc_norm,0.3032258064516129,0.026148685930671746,0 +hendrycksTest-high_school_chemistry,acc,0.2019704433497537,0.028247350122180277,0 +hendrycksTest-high_school_chemistry,acc_norm,0.270935960591133,0.031270907132976984,0 +hendrycksTest-high_school_computer_science,acc,0.23,0.04229525846816506,0 +hendrycksTest-high_school_computer_science,acc_norm,0.28,0.04512608598542128,0 +hendrycksTest-high_school_european_history,acc,0.24848484848484848,0.03374402644139406,0 +hendrycksTest-high_school_european_history,acc_norm,0.3090909090909091,0.036085410115739666,0 +hendrycksTest-high_school_geography,acc,0.18181818181818182,0.027479603010538787,0 +hendrycksTest-high_school_geography,acc_norm,0.2878787878787879,0.03225883512300993,0 +hendrycksTest-high_school_government_and_politics,acc,0.21243523316062177,0.02951928261681725,0 +hendrycksTest-high_school_government_and_politics,acc_norm,0.2538860103626943,0.03141024780565318,0 +hendrycksTest-high_school_macroeconomics,acc,0.2358974358974359,0.02152596540740873,0 +hendrycksTest-high_school_macroeconomics,acc_norm,0.27692307692307694,0.022688042352424994,0 +hendrycksTest-high_school_mathematics,acc,0.1925925925925926,0.024043075181945192,0 +hendrycksTest-high_school_mathematics,acc_norm,0.21481481481481482,0.025040443877000686,0 +hendrycksTest-high_school_microeconomics,acc,0.24369747899159663,0.027886828078380558,0 +hendrycksTest-high_school_microeconomics,acc_norm,0.29831932773109243,0.02971914287634287,0 +hendrycksTest-high_school_physics,acc,0.19205298013245034,0.032162984205936156,0 +hendrycksTest-high_school_physics,acc_norm,0.25165562913907286,0.03543304234389985,0 +hendrycksTest-high_school_psychology,acc,0.22935779816513763,0.018025349724618684,0 +hendrycksTest-high_school_psychology,acc_norm,0.24036697247706423,0.01832060732096407,0 +hendrycksTest-high_school_statistics,acc,0.23148148148148148,0.028765111718046976,0 +hendrycksTest-high_school_statistics,acc_norm,0.28703703703703703,0.030851992993257017,0 +hendrycksTest-high_school_us_history,acc,0.22058823529411764,0.02910225438967409,0 +hendrycksTest-high_school_us_history,acc_norm,0.2647058823529412,0.0309645179269234,0 +hendrycksTest-high_school_world_history,acc,0.270042194092827,0.028900721906293426,0 +hendrycksTest-high_school_world_history,acc_norm,0.3037974683544304,0.029936696387138605,0 +hendrycksTest-human_aging,acc,0.3094170403587444,0.031024411740572206,0 +hendrycksTest-human_aging,acc_norm,0.22869955156950672,0.028188240046929193,0 +hendrycksTest-human_sexuality,acc,0.42748091603053434,0.04338920305792401,0 +hendrycksTest-human_sexuality,acc_norm,0.31297709923664124,0.04066962905677698,0 +hendrycksTest-international_law,acc,0.23140495867768596,0.03849856098794089,0 +hendrycksTest-international_law,acc_norm,0.4462809917355372,0.0453793517794788,0 +hendrycksTest-jurisprudence,acc,0.3148148148148148,0.04489931073591312,0 +hendrycksTest-jurisprudence,acc_norm,0.42592592592592593,0.0478034362693679,0 +hendrycksTest-logical_fallacies,acc,0.25766871165644173,0.03436150827846917,0 +hendrycksTest-logical_fallacies,acc_norm,0.3067484662576687,0.036230899157241474,0 +hendrycksTest-machine_learning,acc,0.3125,0.043994650575715215,0 +hendrycksTest-machine_learning,acc_norm,0.25892857142857145,0.04157751539865629,0 +hendrycksTest-management,acc,0.27184466019417475,0.044052680241409216,0 +hendrycksTest-management,acc_norm,0.33980582524271846,0.046897659372781335,0 +hendrycksTest-marketing,acc,0.27350427350427353,0.029202540153431163,0 +hendrycksTest-marketing,acc_norm,0.2905982905982906,0.029745048572674054,0 +hendrycksTest-medical_genetics,acc,0.28,0.04512608598542127,0 +hendrycksTest-medical_genetics,acc_norm,0.37,0.04852365870939099,0 +hendrycksTest-miscellaneous,acc,0.26309067688378035,0.015745497169049046,0 +hendrycksTest-miscellaneous,acc_norm,0.2656449553001277,0.01579430248788872,0 +hendrycksTest-moral_disputes,acc,0.2658959537572254,0.02378620325550828,0 +hendrycksTest-moral_disputes,acc_norm,0.3236994219653179,0.025190181327608408,0 +hendrycksTest-moral_scenarios,acc,0.23910614525139665,0.014265554192331144,0 +hendrycksTest-moral_scenarios,acc_norm,0.27262569832402234,0.014893391735249588,0 +hendrycksTest-nutrition,acc,0.2581699346405229,0.025058503316958157,0 +hendrycksTest-nutrition,acc_norm,0.3790849673202614,0.027780141207023334,0 +hendrycksTest-philosophy,acc,0.24115755627009647,0.024296594034763426,0 +hendrycksTest-philosophy,acc_norm,0.3086816720257235,0.026236965881153252,0 +hendrycksTest-prehistory,acc,0.26851851851851855,0.024659685185967287,0 +hendrycksTest-prehistory,acc_norm,0.21296296296296297,0.022779719088733396,0 +hendrycksTest-professional_accounting,acc,0.2198581560283688,0.024706141070705474,0 +hendrycksTest-professional_accounting,acc_norm,0.22695035460992907,0.024987106365642962,0 +hendrycksTest-professional_law,acc,0.27509778357235987,0.011405443620996939,0 +hendrycksTest-professional_law,acc_norm,0.288135593220339,0.011567140661324565,0 +hendrycksTest-professional_medicine,acc,0.1801470588235294,0.023345163616544835,0 +hendrycksTest-professional_medicine,acc_norm,0.2610294117647059,0.026679252270103124,0 +hendrycksTest-professional_psychology,acc,0.24509803921568626,0.01740181671142766,0 +hendrycksTest-professional_psychology,acc_norm,0.2581699346405229,0.017704531653250068,0 +hendrycksTest-public_relations,acc,0.24545454545454545,0.04122066502878285,0 +hendrycksTest-public_relations,acc_norm,0.15454545454545454,0.03462262571262667,0 +hendrycksTest-security_studies,acc,0.32653061224489793,0.030021056238440313,0 +hendrycksTest-security_studies,acc_norm,0.2693877551020408,0.02840125202902294,0 +hendrycksTest-sociology,acc,0.24378109452736318,0.030360490154014645,0 +hendrycksTest-sociology,acc_norm,0.2736318407960199,0.03152439186555402,0 +hendrycksTest-us_foreign_policy,acc,0.34,0.04760952285695235,0 +hendrycksTest-us_foreign_policy,acc_norm,0.36,0.04824181513244218,0 +hendrycksTest-virology,acc,0.3132530120481928,0.036108050180310235,0 +hendrycksTest-virology,acc_norm,0.2710843373493976,0.034605799075530276,0 +hendrycksTest-world_religions,acc,0.3157894736842105,0.03565079670708311,0 +hendrycksTest-world_religions,acc_norm,0.38596491228070173,0.03733756969066164,0 +piqa,acc,0.705658324265506,0.01063331147034749,0 +piqa,acc_norm,0.7121871599564744,0.01056325038305919,0 +rte,acc,0.5379061371841155,0.030009848912529117,0 +winogrande,acc,0.5564325177584846,0.0139626949076204,0 diff --git a/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-02-14-09-22.json b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-02-14-09-22.json new file mode 100644 index 0000000000000000000000000000000000000000..6749cdb24176b02464b5cb14ed05788f78c00680 --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-02-14-09-22.json @@ -0,0 +1,427 @@ +{ + "results": { + "copa": { + "acc": 0.74, + "acc_stderr": 0.044084400227680794 + }, + "piqa": { + "acc": 0.705658324265506, + "acc_stderr": 0.01063331147034749, + "acc_norm": 0.7121871599564744, + "acc_norm_stderr": 0.01056325038305919 + }, + "rte": { + "acc": 0.5379061371841155, + "acc_stderr": 0.030009848912529117 + }, + "winogrande": { + "acc": 0.5564325177584846, + "acc_stderr": 0.0139626949076204 + }, + "hendrycksTest-abstract_algebra": { + "acc": 0.22, + "acc_stderr": 0.04163331998932268, + "acc_norm": 0.26, + "acc_norm_stderr": 0.04408440022768079 + }, + "hendrycksTest-anatomy": { + "acc": 0.28888888888888886, + "acc_stderr": 0.03915450630414251, + "acc_norm": 0.22962962962962963, + "acc_norm_stderr": 0.036333844140734636 + }, + "hendrycksTest-astronomy": { + "acc": 0.21710526315789475, + "acc_stderr": 0.03355045304882921, + "acc_norm": 0.3355263157894737, + "acc_norm_stderr": 0.03842498559395271 + }, + "hendrycksTest-business_ethics": { + "acc": 0.34, + "acc_stderr": 0.04760952285695235, + "acc_norm": 0.31, + "acc_norm_stderr": 0.04648231987117316 + }, + "hendrycksTest-clinical_knowledge": { + "acc": 0.24528301886792453, + "acc_stderr": 0.026480357179895678, + "acc_norm": 0.30943396226415093, + "acc_norm_stderr": 0.02845015479411863 + }, + "hendrycksTest-college_biology": { + "acc": 0.2152777777777778, + "acc_stderr": 0.034370793441061344, + "acc_norm": 0.2222222222222222, + "acc_norm_stderr": 0.034765901043041336 + }, + "hendrycksTest-college_chemistry": { + "acc": 0.26, + "acc_stderr": 0.04408440022768078, + "acc_norm": 0.29, + "acc_norm_stderr": 0.045604802157206845 + }, + "hendrycksTest-college_computer_science": { + "acc": 0.29, + "acc_stderr": 0.04560480215720684, + "acc_norm": 0.24, + "acc_norm_stderr": 0.04292346959909284 + }, + "hendrycksTest-college_mathematics": { + "acc": 0.2, + "acc_stderr": 0.04020151261036845, + "acc_norm": 0.3, + "acc_norm_stderr": 0.046056618647183814 + }, + "hendrycksTest-college_medicine": { + "acc": 0.2543352601156069, + "acc_stderr": 0.0332055644308557, + "acc_norm": 0.2543352601156069, + "acc_norm_stderr": 0.0332055644308557 + }, + "hendrycksTest-college_physics": { + "acc": 0.2549019607843137, + "acc_stderr": 0.043364327079931764, + "acc_norm": 0.28431372549019607, + "acc_norm_stderr": 0.04488482852329017 + }, + "hendrycksTest-computer_security": { + "acc": 0.28, + "acc_stderr": 0.04512608598542126, + "acc_norm": 0.36, + "acc_norm_stderr": 0.048241815132442176 + }, + "hendrycksTest-conceptual_physics": { + "acc": 0.2553191489361702, + "acc_stderr": 0.028504856470514203, + "acc_norm": 0.1829787234042553, + "acc_norm_stderr": 0.025276041000449966 + }, + "hendrycksTest-econometrics": { + "acc": 0.21929824561403508, + "acc_stderr": 0.03892431106518753, + "acc_norm": 0.21929824561403508, + "acc_norm_stderr": 0.03892431106518754 + }, + "hendrycksTest-electrical_engineering": { + "acc": 0.2689655172413793, + "acc_stderr": 0.036951833116502325, + "acc_norm": 0.30344827586206896, + "acc_norm_stderr": 0.038312260488503336 + }, + "hendrycksTest-elementary_mathematics": { + "acc": 0.21957671957671956, + "acc_stderr": 0.02132001859977036, + "acc_norm": 0.25925925925925924, + "acc_norm_stderr": 0.022569897074918407 + }, + "hendrycksTest-formal_logic": { + "acc": 0.29365079365079366, + "acc_stderr": 0.04073524322147127, + "acc_norm": 0.23809523809523808, + "acc_norm_stderr": 0.038095238095238126 + }, + "hendrycksTest-global_facts": { + "acc": 0.19, + "acc_stderr": 0.039427724440366234, + "acc_norm": 0.2, + "acc_norm_stderr": 0.04020151261036846 + }, + "hendrycksTest-high_school_biology": { + "acc": 0.23548387096774193, + "acc_stderr": 0.02413763242933771, + "acc_norm": 0.3032258064516129, + "acc_norm_stderr": 0.026148685930671746 + }, + "hendrycksTest-high_school_chemistry": { + "acc": 0.2019704433497537, + "acc_stderr": 0.028247350122180277, + "acc_norm": 0.270935960591133, + "acc_norm_stderr": 0.031270907132976984 + }, + "hendrycksTest-high_school_computer_science": { + "acc": 0.23, + "acc_stderr": 0.04229525846816506, + "acc_norm": 0.28, + "acc_norm_stderr": 0.04512608598542128 + }, + "hendrycksTest-high_school_european_history": { + "acc": 0.24848484848484848, + "acc_stderr": 0.03374402644139406, + "acc_norm": 0.3090909090909091, + "acc_norm_stderr": 0.036085410115739666 + }, + "hendrycksTest-high_school_geography": { + "acc": 0.18181818181818182, + "acc_stderr": 0.027479603010538787, + "acc_norm": 0.2878787878787879, + "acc_norm_stderr": 0.03225883512300993 + }, + "hendrycksTest-high_school_government_and_politics": { + "acc": 0.21243523316062177, + "acc_stderr": 0.02951928261681725, + "acc_norm": 0.2538860103626943, + "acc_norm_stderr": 0.03141024780565318 + }, + "hendrycksTest-high_school_macroeconomics": { + "acc": 0.2358974358974359, + "acc_stderr": 0.02152596540740873, + "acc_norm": 0.27692307692307694, + "acc_norm_stderr": 0.022688042352424994 + }, + "hendrycksTest-high_school_mathematics": { + "acc": 0.1925925925925926, + "acc_stderr": 0.024043075181945192, + "acc_norm": 0.21481481481481482, + "acc_norm_stderr": 0.025040443877000686 + }, + "hendrycksTest-high_school_microeconomics": { + "acc": 0.24369747899159663, + "acc_stderr": 0.027886828078380558, + "acc_norm": 0.29831932773109243, + "acc_norm_stderr": 0.02971914287634287 + }, + "hendrycksTest-high_school_physics": { + "acc": 0.19205298013245034, + "acc_stderr": 0.032162984205936156, + "acc_norm": 0.25165562913907286, + "acc_norm_stderr": 0.03543304234389985 + }, + "hendrycksTest-high_school_psychology": { + "acc": 0.22935779816513763, + "acc_stderr": 0.018025349724618684, + "acc_norm": 0.24036697247706423, + "acc_norm_stderr": 0.01832060732096407 + }, + "hendrycksTest-high_school_statistics": { + "acc": 0.23148148148148148, + "acc_stderr": 0.028765111718046976, + "acc_norm": 0.28703703703703703, + "acc_norm_stderr": 0.030851992993257017 + }, + "hendrycksTest-high_school_us_history": { + "acc": 0.22058823529411764, + "acc_stderr": 0.02910225438967409, + "acc_norm": 0.2647058823529412, + "acc_norm_stderr": 0.0309645179269234 + }, + "hendrycksTest-high_school_world_history": { + "acc": 0.270042194092827, + "acc_stderr": 0.028900721906293426, + "acc_norm": 0.3037974683544304, + "acc_norm_stderr": 0.029936696387138605 + }, + "hendrycksTest-human_aging": { + "acc": 0.3094170403587444, + "acc_stderr": 0.031024411740572206, + "acc_norm": 0.22869955156950672, + "acc_norm_stderr": 0.028188240046929193 + }, + "hendrycksTest-human_sexuality": { + "acc": 0.42748091603053434, + "acc_stderr": 0.04338920305792401, + "acc_norm": 0.31297709923664124, + "acc_norm_stderr": 0.04066962905677698 + }, + "hendrycksTest-international_law": { + "acc": 0.23140495867768596, + "acc_stderr": 0.03849856098794089, + "acc_norm": 0.4462809917355372, + "acc_norm_stderr": 0.0453793517794788 + }, + "hendrycksTest-jurisprudence": { + "acc": 0.3148148148148148, + "acc_stderr": 0.04489931073591312, + "acc_norm": 0.42592592592592593, + "acc_norm_stderr": 0.0478034362693679 + }, + "hendrycksTest-logical_fallacies": { + "acc": 0.25766871165644173, + "acc_stderr": 0.03436150827846917, + "acc_norm": 0.3067484662576687, + "acc_norm_stderr": 0.036230899157241474 + }, + "hendrycksTest-machine_learning": { + "acc": 0.3125, + "acc_stderr": 0.043994650575715215, + "acc_norm": 0.25892857142857145, + "acc_norm_stderr": 0.04157751539865629 + }, + "hendrycksTest-management": { + "acc": 0.27184466019417475, + "acc_stderr": 0.044052680241409216, + "acc_norm": 0.33980582524271846, + "acc_norm_stderr": 0.046897659372781335 + }, + "hendrycksTest-marketing": { + "acc": 0.27350427350427353, + "acc_stderr": 0.029202540153431163, + "acc_norm": 0.2905982905982906, + "acc_norm_stderr": 0.029745048572674054 + }, + "hendrycksTest-medical_genetics": { + "acc": 0.28, + "acc_stderr": 0.04512608598542127, + "acc_norm": 0.37, + "acc_norm_stderr": 0.04852365870939099 + }, + "hendrycksTest-miscellaneous": { + "acc": 0.26309067688378035, + "acc_stderr": 0.015745497169049046, + "acc_norm": 0.2656449553001277, + "acc_norm_stderr": 0.01579430248788872 + }, + "hendrycksTest-moral_disputes": { + "acc": 0.2658959537572254, + "acc_stderr": 0.02378620325550828, + "acc_norm": 0.3236994219653179, + "acc_norm_stderr": 0.025190181327608408 + }, + "hendrycksTest-moral_scenarios": { + "acc": 0.23910614525139665, + "acc_stderr": 0.014265554192331144, + "acc_norm": 0.27262569832402234, + "acc_norm_stderr": 0.014893391735249588 + }, + "hendrycksTest-nutrition": { + "acc": 0.2581699346405229, + "acc_stderr": 0.025058503316958157, + "acc_norm": 0.3790849673202614, + "acc_norm_stderr": 0.027780141207023334 + }, + "hendrycksTest-philosophy": { + "acc": 0.24115755627009647, + "acc_stderr": 0.024296594034763426, + "acc_norm": 0.3086816720257235, + "acc_norm_stderr": 0.026236965881153252 + }, + "hendrycksTest-prehistory": { + "acc": 0.26851851851851855, + "acc_stderr": 0.024659685185967287, + "acc_norm": 0.21296296296296297, + "acc_norm_stderr": 0.022779719088733396 + }, + "hendrycksTest-professional_accounting": { + "acc": 0.2198581560283688, + "acc_stderr": 0.024706141070705474, + "acc_norm": 0.22695035460992907, + "acc_norm_stderr": 0.024987106365642962 + }, + "hendrycksTest-professional_law": { + "acc": 0.27509778357235987, + "acc_stderr": 0.011405443620996939, + "acc_norm": 0.288135593220339, + "acc_norm_stderr": 0.011567140661324565 + }, + "hendrycksTest-professional_medicine": { + "acc": 0.1801470588235294, + "acc_stderr": 0.023345163616544835, + "acc_norm": 0.2610294117647059, + "acc_norm_stderr": 0.026679252270103124 + }, + "hendrycksTest-professional_psychology": { + "acc": 0.24509803921568626, + "acc_stderr": 0.01740181671142766, + "acc_norm": 0.2581699346405229, + "acc_norm_stderr": 0.017704531653250068 + }, + "hendrycksTest-public_relations": { + "acc": 0.24545454545454545, + "acc_stderr": 0.04122066502878285, + "acc_norm": 0.15454545454545454, + "acc_norm_stderr": 0.03462262571262667 + }, + "hendrycksTest-security_studies": { + "acc": 0.32653061224489793, + "acc_stderr": 0.030021056238440313, + "acc_norm": 0.2693877551020408, + "acc_norm_stderr": 0.02840125202902294 + }, + "hendrycksTest-sociology": { + "acc": 0.24378109452736318, + "acc_stderr": 0.030360490154014645, + "acc_norm": 0.2736318407960199, + "acc_norm_stderr": 0.03152439186555402 + }, + "hendrycksTest-us_foreign_policy": { + "acc": 0.34, + "acc_stderr": 0.04760952285695235, + "acc_norm": 0.36, + "acc_norm_stderr": 0.04824181513244218 + }, + "hendrycksTest-virology": { + "acc": 0.3132530120481928, + "acc_stderr": 0.036108050180310235, + "acc_norm": 0.2710843373493976, + "acc_norm_stderr": 0.034605799075530276 + }, + "hendrycksTest-world_religions": { + "acc": 0.3157894736842105, + "acc_stderr": 0.03565079670708311, + "acc_norm": 0.38596491228070173, + "acc_norm_stderr": 0.03733756969066164 + } + }, + "versions": { + "copa": 0, + "piqa": 0, + "rte": 0, + "winogrande": 0, + "hendrycksTest-abstract_algebra": 0, + "hendrycksTest-anatomy": 0, + "hendrycksTest-astronomy": 0, + "hendrycksTest-business_ethics": 0, + "hendrycksTest-clinical_knowledge": 0, + "hendrycksTest-college_biology": 0, + "hendrycksTest-college_chemistry": 0, + "hendrycksTest-college_computer_science": 0, + "hendrycksTest-college_mathematics": 0, + "hendrycksTest-college_medicine": 0, + "hendrycksTest-college_physics": 0, + "hendrycksTest-computer_security": 0, + "hendrycksTest-conceptual_physics": 0, + "hendrycksTest-econometrics": 0, + "hendrycksTest-electrical_engineering": 0, + "hendrycksTest-elementary_mathematics": 0, + "hendrycksTest-formal_logic": 0, + "hendrycksTest-global_facts": 0, + "hendrycksTest-high_school_biology": 0, + "hendrycksTest-high_school_chemistry": 0, + "hendrycksTest-high_school_computer_science": 0, + "hendrycksTest-high_school_european_history": 0, + "hendrycksTest-high_school_geography": 0, + "hendrycksTest-high_school_government_and_politics": 0, + "hendrycksTest-high_school_macroeconomics": 0, + "hendrycksTest-high_school_mathematics": 0, + "hendrycksTest-high_school_microeconomics": 0, + "hendrycksTest-high_school_physics": 0, + "hendrycksTest-high_school_psychology": 0, + "hendrycksTest-high_school_statistics": 0, + "hendrycksTest-high_school_us_history": 0, + "hendrycksTest-high_school_world_history": 0, + "hendrycksTest-human_aging": 0, + "hendrycksTest-human_sexuality": 0, + "hendrycksTest-international_law": 0, + "hendrycksTest-jurisprudence": 0, + "hendrycksTest-logical_fallacies": 0, + "hendrycksTest-machine_learning": 0, + "hendrycksTest-management": 0, + "hendrycksTest-marketing": 0, + "hendrycksTest-medical_genetics": 0, + "hendrycksTest-miscellaneous": 0, + "hendrycksTest-moral_disputes": 0, + "hendrycksTest-moral_scenarios": 0, + "hendrycksTest-nutrition": 0, + "hendrycksTest-philosophy": 0, + "hendrycksTest-prehistory": 0, + "hendrycksTest-professional_accounting": 0, + "hendrycksTest-professional_law": 0, + "hendrycksTest-professional_medicine": 0, + "hendrycksTest-professional_psychology": 0, + "hendrycksTest-public_relations": 0, + "hendrycksTest-security_studies": 0, + "hendrycksTest-sociology": 0, + "hendrycksTest-us_foreign_policy": 0, + "hendrycksTest-virology": 0, + "hendrycksTest-world_religions": 0 + } +} \ No newline at end of file diff --git a/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.csv b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.csv new file mode 100644 index 0000000000000000000000000000000000000000..9553d71a5d07f20448efbecf6a2040d58f3bff96 --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.csv @@ -0,0 +1,10 @@ +task,metric,value,err,version +arc_challenge,acc,0.26535836177474403,0.012902554762313967,0 +arc_challenge,acc_norm,0.295221843003413,0.013329750293382316,0 +arc_easy,acc,0.5896464646464646,0.010093531255765457,0 +arc_easy,acc_norm,0.5404040404040404,0.010226230740889027,0 +boolq,acc,0.5859327217125382,0.008614932353134947,1 +hellaswag,acc,0.40689105755825533,0.004902502514738602,0 +hellaswag,acc_norm,0.5210117506472814,0.0049853735507751065,0 +sciq,acc,0.851,0.011266140684632175,0 +sciq,acc_norm,0.795,0.012772554096113132,0 diff --git a/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.json b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.json new file mode 100644 index 0000000000000000000000000000000000000000..5c49987e0ae40ceb93f55c20464b04a24bbf1933 --- /dev/null +++ b/3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.json @@ -0,0 +1,39 @@ +{ + "results": { + "boolq": { + "acc": 0.5859327217125382, + "acc_stderr": 0.008614932353134947 + }, + "hellaswag": { + "acc": 0.40689105755825533, + "acc_stderr": 0.004902502514738602, + "acc_norm": 0.5210117506472814, + "acc_norm_stderr": 0.0049853735507751065 + }, + "arc_challenge": { + "acc": 0.26535836177474403, + "acc_stderr": 0.012902554762313967, + "acc_norm": 0.295221843003413, + "acc_norm_stderr": 0.013329750293382316 + }, + "arc_easy": { + "acc": 0.5896464646464646, + "acc_stderr": 0.010093531255765457, + "acc_norm": 0.5404040404040404, + "acc_norm_stderr": 0.010226230740889027 + }, + "sciq": { + "acc": 0.851, + "acc_stderr": 0.011266140684632175, + "acc_norm": 0.795, + "acc_norm_stderr": 0.012772554096113132 + } + }, + "versions": { + "boolq": 1, + "hellaswag": 0, + "arc_challenge": 0, + "arc_easy": 0, + "sciq": 0 + } +} \ No newline at end of file diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fd4f06fe913e7699adb3ab634d3476023605998 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29fbd24b355bea1889e32dd263759d483b32734bb1972d3207e8be072849c9a +size 95016023 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d3a53ea64036f3b1535bb58799bc393b3e4f86e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b049d85994023c23eba0b9d2404c51171d424aa01245d8cd93fb8b94b861fdd +size 95016407 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..55245280db6f7b87936253301fe058cf8b901b95 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b54022ec72c9582df13e6e31f1a6ed060b4fce63a986aec7234e756a24ff7ce +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ce3857d5e16de73bb42950b4f66b975f3359dc6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f953b34095264a475d8e11d8d5ebaae8600f027ea1d3b4045659a12878b507 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80eb552faa6f6d74058b66a74c50745515172de1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b90f4da07c01695b5c96664367c860f76c1cbbc6da3cf2b8cf9063d3201c22 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4df6a4153a9a8fab97d94f69a832f07690891ca --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b215f52d2612e6951cfc5b8127679b69ed7c805e9e7c339942d94d9e8b6c853e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..07dce34aee8224c806f8fabd690ebc8f6ae3a221 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a16699510b0ab3166810904861d998a15c8790db4c8e2858fc372a74c6b2ef +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b4fd5a1d64ef19d52437d2e19cd731e75561aa0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4849707bed7ea018d0a4c7ceaabe4177f3dfaa874ce77f4c0638724549d4fa +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb716ed9a00458c6429802565cf2e4d2021a475e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c015e504acbd2c5e60911087b10ec281a6191786860feeed6c2c85eee9118da0 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b1a7cb25b2518b6a7874676001326b9013354b1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3871894c131010d3f845f2eac45e7794bc808fc353a2e12b98386026b1724f +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..485f84b48eef8b83da51a2a0d40b57426d2e20b4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a6f62b9427cbff50821ade3d792b84818a12c3f01f597d94945d79c6719fd1c +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..300266e4d171b87048cf8861d8ab191447ee06cd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9a83336a48a661294f5cb9cc859a0d66cca4c15eb3361498b405edaa524f84 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51aacc8240e3bb3f97e630c0268edae180d56aaa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c696cfbeb527257264d8d6a35dc7692fccb73b1d970735d7811b24ce568b3b8c +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0beab2c575f42dde6cd3f390b21e94eb5c5bf97a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8380086d03c69bc6f7d39793cf0c4e999903953a56a3c5f2f2de955e554fc3 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7385bd12cac0f629d8287da021fc808e5bacea41 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0d66ac9183255cc40ced499db1222e2db3c89250b55f53f106d713806615e4 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..750b89e6a67da9b73e5b6ac842594e347c96b771 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a89983e7bb35da7884615a40f785cf49f12e39fc095204e1fe19e67193b1c1 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb726ed3464c67771c2d412365ed683de6024bf9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0599ed0ae07c775b652e5ec04088f9fd1e3435ea502e7cf7924a4e85eeb57a1c +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04231fddc85d025750d1a23f6c68526e62371bf4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c900173603d7dd19faa0fe74995226801013fcf82e3afef12bf34216c0531a7e +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51020401724c46da2f866c3d6777b736659febd7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d52946ac110c881029f050c7d1e00fd5f2b680a882e39c14df45da435e73fae +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98b1673febcf0d125638cd20bc05b9bdd946cca6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee9b906ea4f0f7bb0460dae8427a0a21eaaae7842fd9ba5ef1447fd567a5d2e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d3ec3f9b8f646fdf2c213d1ace869a420d3dc75 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc535b58fc224dd1cdc2fb1b5fa4b66c1acbdcaca435884425ddc7b8ec54886 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67afd5ed523ecf915ead903d09386e271cae4641 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0641f5b851f1592f6d16eb5c2f4ec17fdc16c5e237d4eb349262eea73001d5b2 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1a320c2993b306f87bd371890ceb53cc26e6338 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3523efc349ae5ab1899f6162a70c1870387adb9986abcfe2fa2390065f360a5a +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9b0af529458affbcf5e3111a2c4027ef512b5bb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fba351538a1aa9045b7013d2aa8fdde2b97a769fe8b9ec5d2be6c430e9d6b5 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8afd95d4ec800f2ddc722089f00ee7370696cf4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df7370c0908abc119ebad2983e149fec05ea113068fd71689c57ba6a0d82da2 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9778fe23a072c3868ad422c5968c2e99acfaa88 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8471a8ae65b6bc287ddc06a6ca9e213e002efca6f5e0051b8f4c5a1ebf1d0c59 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..114b5598d7b6d120e666fcbd9df0eacc4c696f52 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c67a06d5f8ffedbea94f8d7395f36c222683cc3fe6e3051e387ae1b39acbde +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad9af99c6aefeb9b9a0bc8a60e661e69601f7eb4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbe0a6fac28e62c266236bc0342078cff6717bfaaf5690a43d638d894b647ae +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b95c16fd42369660aaf7d2b1440fa5938b58259 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b15c8ee479c7173289455af05e99230c2b8659a1eec826a548f12c72a1a009 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b504515e19b3bcc0c093a0892833c9275bdc971 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801a2addd491cbeba1fa75c035e961dd4241dd0ec5e4aeccbc95a0896cc41f67 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08ede8ac1609e5fd97e89db575a920f89ae249f9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb80da486622ac7ccb63093e6034b1799c683f9c85c9af54d56d0c067fc3249 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..18718afd174ac89b60c57488f043b0a4671748a9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19838348110bee85b68ce287bd14a230e3887435cf8414f9ee06bf91a737a03 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44014c987ac9ba27e633ec9674943f36ae755408 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8a73bfd2885fb5e9c6353e7fe0539a43f2976aa98114316d017b202b8cc817 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bbccd000fdfa7a6b3bad263b13996d53cd3305fe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16417fab42c658d2bdf1eefb6dd771b315b9fdb04c29cec9a0bb7fdc0ba117f2 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbc1077c9cab0e9ddacd92f613fd2c279c25e970 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63d4328db902e7bbb9a932a90c0c17380dc4d2cf2ced33a56eda0e9dfd9470e5 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54f1eabb32c8410ca71fc1710e477a707c9a1157 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c79f278d8fb9d8b5f1a57a31ac5b74470890af3e88bb94abb27f41439e66a3e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..542475ed0977c2b9a46f2c384cd8f35522ca0518 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f0f92b6e903cb07bedb26574fb8ae7dda99ed5a46ac7a6783869487edcbf98 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bbb1ddcb4e24021968864bac43f6438f71b03e5d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1846c6c771081ddbd642053a96590e5fdfd642f01ac141d1be43060ae4d29cf +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..339b12cad67d63f945dcb1c962312685184e25fc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c034732b37f75f30e1e67e5c91e22d3e984ad5ccdfb342f1209fc16d52f520 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fcf921728992f93f6bd5f056cecbcf41453a0628 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef434eb7c5a2c0e5a3e89001916acad5a8ef2da4cd7fd9cacb1312fd59e80cd +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e81729d2a7586880452722b2b96d2dcfbcab7e6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e93825d773e0c1c1a725f827a9867edc8faf40d46cbf81b40f97ce8ee8f68fe +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3853930d69060ca6958781c0d07db55cbac925d1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea553a9f586278dc11a3e2d103820f446129281d2c3875397937b5b3cb753cf2 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb45de67b9105c2a7f30783ec11514d131779a20 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262e99597c557c99e102b2e42314d1ea289470adedd7c9a6c537653a3cf52869 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87b5e735871e0fecb27e52060631d9513cc0becc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c97a25ec429af9e992d7a5b2c0e0ba354a38327699d2b131acdc9d297fc70b8 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c334e400d2c404458a5765f35cbf6fa0657b50b6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f325516ed422a64e545f8579303f00c2fd40f506254f0adc28c43c94e9b6e12c +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..929b999fb32d57a9b46c688356cd14a557de25cd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91210069813109fdbeefc831d4fba1bcd9905e67a0b724125fc260a754071a8e +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b40065b6e5b3a63b1d2769812b207b764511944a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bf17c1eeec0d92e3ee846e6659762e84eb93d4af7991c1faee24095226acc0 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aa9a6e3f502b364dc470e556b28c793bae13b3b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c1571e07dcc14ba11adf5a22d9e2b866806ab1f7ef9afde9d441ce714be3e5 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2404d1b3bf761e55367e149dee1889ec6fcaa157 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33dc928bcd065a28211d1b98108fd0cea1d996a49ea9bac989ac24031dc721a2 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..232f77ecb221f841c6404ec547d0d64cb799b4ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3878c149a7058e4015a55ad1951bfb58b19019f73ce09f802f9954d5a7b68829 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3bdf3cd57467c1c26b3273da9f9eaa483db580e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e93099257b5d92cabee1666b9338e99fe4a0d5e2aa381303a7a2219c9980cf51 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0262e5e397b46723bc2b0e28d9f93dde2c8fa01b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84817400951737aad801212bbca745130dae70e48a2cc0f6940ba6c4267b4c68 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d761b20e8a163aaed85195d7149fb56a50849470 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b202b59301fe290fd3dc076c27cd1e036bf1ee25e6bdfed522bc758b7941d4 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a43bd62ada360fbee19063928c92314c2be7600 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb844747c34836c059da0c570f2ad6b21e03aae0314912f8e412d884ff6b1d15 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb355c47f6c53fcc90eea05f47ec537d23d3b44e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427f72982924ec587a783563fcf65d1a535dad29197a92269d03e7bfd60535c1 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..65d7f8c6fb50cd7d15a593a24d2b850a905e9d02 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7537924d140f2abff3f0d883d756a5ed70d8f3e5045d8721d75a545d223c8d +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d224a2d3eca39115a55b2da3a67f68686d9f61b9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c7d61d1e0d6b1092924ca50fb24b949386eb1b7b6831395e45d90032331a3d +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16d92c87fc7785a01844fa1e250dde88a834b695 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5658aa0febcefe7e00cc1322e0f854f14e998548a3288e1d2f4946ed81cbc9e +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e6d5212f469371e31f08d2ff93d3d7aebb6ec14 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33fab0af752adc536d233da985f89087f903c2e388fe5994fc34299ff4a58252 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..437b9e6658750d5db784f6d53bc8d34493f9eafb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b77d9650168dece7363193f1a0313db8cd05c6363fc1f008bd5ab5b5ba3c83 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a71179bb4da7c900779cd2057a7a2029dbde65f1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b86ee7aabfc8df4b754aa8bfb89c6916d9c032bb406d5270f2076cfaa801cf +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ad6ad43ad23170eca143f3d0ed64ed756c6f1ff --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd1469ec67b44197767002af0d892e2aadf303eed8d2fa0f2540b1b51f7eaf8 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f16cc631ca85180237d4a35a7240f5dcd03eca6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7b767e26bdc4c149f8847c11594295e9e119380bfbdbb59d982cf5b901367d +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b14761fc01bb889e144dd5b1634defec634bef6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79114e1ed8bfaf28016a944b234e3ef5b818d2ae2584e958de5f7807cd540270 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5025e9aad22010486632ad1c4999871dfad22074 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a73ee12ab9fe33004a21363e4f0bd3857dc27a9c78fe7a7dad2304a5afa1f01 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a388d093f25fce91928778fc38e317c3bc0853d7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce811e07f3261a026ca3c4ee0d48bff223f3b71db0192cd8a826e85a7f55fa4 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6169bbc788584d74ee212cc97c90c6356e17001 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181372cf63ec6839e3d1d517899eb1a32bd7b49cbaf8fd1380a49dfe186b2c41 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a131300ab3db27dd03c3195e596ca0bc817727c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a350c09809d091349b7157e9749218d61bd3f71e71280b753b26ff4177ac2a93 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..43d15e9e407c1f81318429218daa0a50c9057ea5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6764231b71a40844ab53b8f6c522eee9e5f2143add83bd9efdf8ef1299b2c90 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8d7258431d041ebf5abf94940e6ac4476e43d26 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c5c77090dc3324d154d057e7a84d23513b3a912281395ab1bd5db595a52bd6 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e56715f96e47ccfd790639cd04e1b67761a8a33 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6c62feda2957213af05953b8337aa874d8bc1cb22d36251a07428648f34d750 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3fc2b74df504791e8e28affeacb9215d77fcee2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a569090d207cdd3c918ed0219013f5113bdc92e6bc6c52c515278e93db6dc365 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a7e5ee7d90f4dcfc9d92f22fe4c41a1fae1dbac --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49916f23fd227cc93b58a5014b45c780e42e8a1fd9943f32c341f941ebd7210e +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e17a6177024071f4e13b8bfdd0bc1b4cfc4f1c75 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f3ed7a6584be973775c5c30185364e8923542563825402dd69a2130414363b +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4abd28d31e051dc12b822e80cbfc8206253e5de6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ecad323a7181890d1de5e05b85e9a303a475cf654f891e68d5672717f20bf4 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2351ca21aac4267ee23f597d1f08998ec8397b3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787061d74da0c6f19c8ca3d3fd1f9c2ce3c5177a56cd73b62e08891fb157e6ba +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1765bccc12a3a48e57d43230833a9f098e8cee21 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8622b9f1e98978230b12f3ba3819486d33bafff894d63936e46475235536ecdd +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a033b1e145d5d094d11e7385aa1c1b0a11159118 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951dfb7e273cbbccd4b55ddf84132538e63611f9f7af4cd8b50160556d931af0 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd5a0ea01666760a08acfc46b671e258b6bb78cf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a3acbc74985ad1f4b8ea17f6415e7ff23b7e31eecee944c91f6ebb9b68bc59 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..522a5b5745a514f2429f4abdae678b2fed054312 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb507fc42adfe2278fdc1361554bc1d62b57758a31f7ee09936de50bfe094e87 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e44b0495b0fa169748303635a3eb6cf7c9e0a0f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb7c49591d35a70c99c939ba70b312246899ce77a67a9cc251086b18f1228c0 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..550d7686efb444a970752f655ec57cd279969012 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480943b574c8652d2f8f2b49405c1a4a50992da8cb3ca5bf2f6d7a198eb0824f +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8f09e074d9a2a26d9831b4bb350ca8af9e706a5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65381718bcbf5204f7ae7cd5229c0f34f894fbe373a8e33354f9ea2f20570f17 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d5f81ac9e34e970bc9f7c891e2209e6a53bb6f5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033069a2dbd605b687788c29cd0694ac2dad637df9ae7096c3f26d5c3546678d +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d1e9520f6851fa93017922cd98233b94293add4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b873ae33b3aed2af0c4689ba87964233355fb0b7dadc3c3189e2eaf70bc60b5b +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b201a88de4280979b14165271e3db4d875e4faf2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47a1010a1e0412914c4a6084b3f960c509fbd3f613e7d4020f71ea357531b28 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ed7750a633236bf3ea20aed8e853a191b1cf7fd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c0c1124982bf8b9c068882e6bac2d4de98d890de487f8dcd76376c17fb03b3a +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e86838ef8ee55455d06e6d18ea05299247030e5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1381b3eb27d581fea384032ca21633be8e142e2794d8b9c14e568bd52ff768c6 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2970984be201b18a61fd2788a2f23a12715ead72 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b66643e47f87980ae2469125aaca09511dd7a2bc8f4c7fa932de3af1fda03b2a +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..52bafd66664f687b3e65e599afe4410122c4d64a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a53399dde8c3dcd4b001922548edaaa61dd6d8dbcd0ce61364940053ebcfedb5 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a64471a6beab92668ef8d427821544672383b14 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec199887099e7dfa381197c564106fabe556d09d028e36f322fcda054def97b8 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44b63f203fb3fd519a0e543c605298848f58d80d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7827ca19821705a2d29df816adaef57938bca660d0d46fca3c633f655a5649 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dea219f540fab8e0cf63058b09bf7008f919a473 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c41ca52cf676d13d525e7c29340e35c8a0845fd32013362fa7dbe76c48e590d +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b3f3ae2864baf1ffb8f121182f070a6b6828cb5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803045368cbc5b86f20af2a64fc8e3f21f5ac851853a5185e2571feba06e544c +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..688c8d418ca2a08323e01e67262198ba825900e0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41214b12d2fbb9b36f446110ea6674712af333baeb7f15b407da0ec523454cd5 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ed30f26ebeaa2ecd53c674eb05afa8e6001e9b7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7042ebf923d47586b877410c68eaec179650af36bb974b30eec53eef1b5a24 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e56e4522dfd7304c48a018e1904790bdc3a0567e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2157bd336f65feb9414db163f91ca3d0ad0049f976778c2cdb23677328f26b83 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e71945051935b8bec19fd366d90482d382a1ee9d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d89423ffe54d00ee0fc75b1659758565d558826400e5bf3099712117b5ded43 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc009b71c1571cfe6a3f6d118de1fdb54943914a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469dcbe82773061f893e6772f1fc20d936058fe23594b88b55b6305e37e7f886 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84a20d93ae6316810b36242570a04abc8ef65443 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0516f50d74f5a7b70874993cee3ad58a96823c95e3ea28228bbd66a555dd9798 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a3529890b5082b1b16702ba333652e7ccab3b08 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d90072f68df2186f5fa6165a2c3273b124310ae2790da07fa5f390b57a0f1dd +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6b8e77b54405c66b32628efaf9f76518412029a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e07966545597e9e466594f66ab77d2f36451307d2bb8860400493607e673ab6c +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d199cf0c62cb41306a27e515aa577308b92edc8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a7ed6bee760d404d27e8437c4be4962270e849c05df859bdc2eb86712dcf34 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fd765e25d435b1ea9d395439a4006c1809cb9b1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03847411d15aa647265beda8747d497a8d9236f5ad6e49d3934e8fa11198f9e8 +size 95016621 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8389a96f2ef46af9cc7bf63299b7ea6a8577755 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b723cffe1dc1c62912e229ae8b93a781187c7e327f54008a2d186916f2fc4802 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c6785e22663b2b5e2768852b78a1d30a8010ba2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ede7f2d7487174849597ca142870f317ffdcecd52593f93a09deacea0b1af0 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ee8e896bff758530750859e4fa5367f594fa9d6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123fd9dde26916fa6ee23e372758a8d792e2689c7227872edd12310fa8c205ac +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cf8b1c8e9c4f750b012b3f804d34ac8234815c3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdad2962f952699c439c680fa343e3ba1afdec55b8aa01e4d82c61d15e631047 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f9b36698254e9a1ba4b3d410e57ed9695010c95 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc3444c62be25906ea165e9491e459b1141cfb987999e8cb1c13cb7dc807452 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa7c6bbe4592ec13d06a235eeacf1b87e9d5c4ee --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa05c65c3c53d80aa0a97dad38b4b0e8fe80e85ac79dd0b5cb759170b70adae +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6c0b62b45eb129f8d60d5b725b9d155ba89bcfd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37fed7f96ef99d918e0a45573ba862f4fc96d02de042470f256285920ad30049 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36b291d31ff7de3e5422f01e1345437b959ca179 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6121eb18ab6b5cc4008c0b74a0f8bc9955f06ea8e4dd25f1c80f3c7112be8bef +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38f092494250059f77a9a0dc675c507f76707ac0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9c400a9f6f69b4c2f9355ea21f12ef9136b3e9bd39f3f8c98955874f649de0 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2024522b428a27a15c74bbdf3b7023cf81173c3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6a627acc030c2cd6db37f6131ae748329bc0d1ed620696993926421d1076f1 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd5ba4128fd49eebec18ff2c378f4c8f810070b1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945e9646d0f6db8fa04413b65ad42c5fcec4d0951de00de844ef827b3a3d7e21 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67d5183dc375176de7a1a7f06a1072328bafb2d4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15653c1bc30b5030fa60c8161f3f91c3494f484260fc705e2bbcfff007e7f17d +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e60de451c576ea9de1de69272e451142242e167f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0601c41d416a80ed6b1363aec339fffe679db5a15ff141d15a28315ea15db822 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ca6a0861190c872a0cc59943c9cde10b285110a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8836e6f9f917606d7e3dcaf906b5fec67df13c916db34dbeafe81acfc1e6e44 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c53b3e961971fe7016bdc73740617a4554e8a1ff --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c78d1ebd7f0d64668a521bf46933c82222d64be83766cce7c508010e86224eb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8003be85fe43e84e0d2d0e6b312b4a33bae2829c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf4907605313e660eeaaa3850fb68c5f98f8fce812f51f3ded312e279faf4cc +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f14b9b57b7b4c8316931b8f77e1bfcbe85f50bfe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a5f84950aadfa293d73a665c0fec2f46547c47a19bc77c863517221f4c732c +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3102d8f5e61865853af6f40b7e49bcce15c670be --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715af3e94e3bd124a853012f539bd95795d2960bc2c01f7a4f20101c01a5e074 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04deb295687c95b62b40d04e53d24c61d2940c8d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544164593dd9642dcbd85f667282b4927ce775eec19c783c0e6c4b016d88f032 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..316d0a76d7c8a1fd3ee8321b38d10f43b3d227ab --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541f685999c539d5e1e3420fe1321c066b033033e132851d6f7c0ed9b0fcfa08 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd35c02c01bd9ca5d9177f653617e75335ef0843 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ed36fee89e1f2c2f044517ebe14034510bbf73dce0f65a058a9aacd69429d2 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c30f8f04d4e7d28f6d6cdb0b035c12cf96b4a89e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d86da64527c3d70287cd0d7bc4a82200227da43dac724126b17206598360e8 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca743f27182299ebf039bff675c1a12b935f91c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45fc7323fc7a6df075a2eb5a6cdfc1678b91613f7147485f2b29f1dcde2f3e65 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dd0b57fa12d903780aaab923f800dee3ff67100 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd0a3b2c65ad3de3a88c64b021424a4126f31972ff84272b1f33cf42343837a +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bc104c2d7fa5238b160f3e092c1fe5086e7660d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f373a33a65624c718bf76c4e1a72fb785a95735a7db5f94ceea710efd6c499 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5445545706cbbd117f1bc946e75fb2403f93e6ea --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e33fe5829969834af12b0384631c8708fab29a6fc0e0284e36cb000e0d58a6bc +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c2a5da9af792012466e3d64381013d2ccd8fe1e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea2b021b1bf0d5c4328e8de6e441d591263bc0a2eee0c3d5586789d479a441d +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dfaf1e470dd79608b5c6f41001eb89770480ef0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e008a6310230b44bc32a5dfefba2579f02fe9b40fa6d15675b3da89f7de9c3e2 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..542beb45b8042adce6e529f61dfe585ad15174fd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52bdc7ae3b94a8a357c2dec4db8b2e116b91729dc19e922d15e063f0579234c8 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8c0251bf48d7eff0617e9dea2af4f40fe13ddd8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15b694317e749b5df22857c34b753dcdaf6572508261bcbac2cfcfaf3efa813 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..790c9d478cd2e7d48aaf53a9c707e05cc663937f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9deacc6c16fa1c3a8296bdad8350fe7054cd24c0d4a1837f47edcd9550eaaf13 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ed9abb4d90c732263f2eff9b58d5f95faddb5e1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c8027fe44bf10dfff35bc96a57f7583a76f1d4168e42dba0b28f62f68edf85 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a0fa3f62bab261379a7e6d43c194315a8f513a5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7115066a4c5c9edb4863085615659e89f2f8c9ea97b376f05fb8b507f47173 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7fd90d3b3afccb55dfa531c1abe0c868dbb75041 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b0ca69c9fc8ce0ae1270e1d1c336c833f837a88225d57a9499595b0b5d60bfa +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36f49ba8378a34c4063d5950208d4aacf58e2666 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:910ee0776ee403b3b674143e04a5e27c44a32eb1275a39645b5605fd13632674 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80ca3e23f16a8825f1870776c782ab0459adad7f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:479a42686b0d29f174c489d112f6107fa8e046ac04fc83c9b043907ad8826269 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e176ffe9590ccfd69c7ea42473e2bd5da7ba735c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e99d86630c96408a0f112a0ae4924b2d77f0a8b8a517c5f578e95fb49d4a71d +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34f130d95b948c63fd2c598649d5cb66ae71cb74 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5330df5dfddef6592f5782f5003e76033fc4e41340cca1619fdaeaaba3e8022a +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abd478875173a7ca7a32aa6c85f24e53eeefc7f5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2bd09054a5f3546c8036dd62f8d5402d8e26196faf859c1fdcab20507d1ebdd +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f03cc95ff606d35a691426dcca2e6bb8f056e724 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cdd68a3a73cf9b66c44cbf0fb9bc45fe39e6f0112f6b9099c82a04652ee6b47 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebfed578a313fdd8f368940de8d99f1a510daf94 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5668acd76dd9f6d85f56beb327a9b6a54d02a7f73ebb9257cfb6ec21a592afd +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..851ea904ae21f916953883f78faf939797dc112c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f2f32b911f923987d0f3202220a0b70a4816b4b517e70ebe93f7749c199541 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a73b48a3d1cd7aaa3bdf8377fb405f038e779313 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72132a231935b67c1e74d049e3827445229282375c025e93b0780e7b10b9e2ac +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69b1b702ad2deb65e6ea9186095a9a053f15c300 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b89c207e46098c54e9661d06c244b20a76ca1a43387318da8ea8fa77ddfd2fc +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..02cf3456869a4ac1fb038184de37997081fb47a7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbcea0fdf75081b5b04003b98e9d41def8b22b72864644ab68b52ff26ee0d3b +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20bb9a1e97f103ad913580ce3d9b206634028e25 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4423217cb0322661628f18e856c239f12d53cba0b2c8d615861c33e2e9d4c511 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da756a59aedb041061446bfe6a8b0cb4d42751b9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983f47efdd23b8091feb1bf3a2f742a27108d692e6c85c1cf3507f6df99fe6fc +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73306b68e4a6a60cb19e2c7f0d522ff965d10699 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ead9f3cd8d0a18bacb6485fa2d345e9903838b17a9be3e8b530c3245a74442cd +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5077634e490bbd37e0a97d739dc3ca3da20dcf61 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:958a1997eb07447153578e01455a55341c54470621a7c9062bb67f6d3fd384a3 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..55a38a48fd2b41fbb80f3ba5af8614d9567a6b0d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179013645312c1cbcf0d3ff4652304f2dbedf7a0c1b52bae5dde0c8b3e4303c2 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dbf5ce8cf51134fc6dd267e50087b4b6f659f90 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6fcdefd10bf4d73c0f922f2500692e22c907ae636c6b698ff0a79fe5c992fa +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e7085ca5f09dc9ada3eeb72c09916a89fc58759 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9a3aedef5b70e4157b367aefbbed88b49bd32a1958ca65d5d446784defd739 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c22a7cbac182c7edbe88d38e007d4d298dde64f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a24d3290995424e36217c02afa30f63456ca6a64cdb50be646fd03719507d26 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..462c7ccfbdcea31e706f879bf976a83c90daa12d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b3fbd9b51613d5dd4e146aeb0f54e1363fb5ff31f5ca9b313dd65f7aa77fd2 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6449f6fa3d0bd5c27b45ab780ec565a34ac9fc3f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37d6b20d4102044321d834b9496be3af013bf82f8224b4d328746cf6d0d7057 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a1715c059ada47a587bc257bc3f582f55b425e2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f84769468a1422fbdd4b3dedf6d1d9002fc4e1c7bb6e6f0aa688d0e1e79bd4 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c7d6e51b630abea08c47dae8cbd8b7d961f09f0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5a7b71f8e8e83bfb077222f3ff13fdeb6236439183e40a0251a07d597f7f3a5 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..059d42fe9c6371b264648c2821a8c570113af95a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91045018dd7c44b45207655f4fd5d20c50bcc53eba71586d2ae3eb8c1ad36596 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..45a503bf7b1e94c4fe73e30ee6878a553da3221a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fad1e6cd0a9ae37564181f58fcf0745d5407089c09576c2ab28a70b240af737 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01b7d584deb36b1838dd1eb173a2ff1571e65e6e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b026093b2f608568156d550f9cbf09b0cba14b063bb59a426d489d30fb29871c +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df80105620093632c4c9f4342882d281aa1331ca --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228dc8afa926baf0bec87ebacc5866ce6e58955c1af52483e8eb96812c361291 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e9fb725ac481b7583d8496e8905323c7db18adf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f494f74df1eadbf05b510ceced92aded2612d7aa5abfb2d35a27731777acec +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..355ed4e9c814ca2822df47d638599e72dcea74ab --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7413521f3baab8cf0f0f3970270e80ad5156fe7e2913e47317725a18d8dd75 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3d92b54c85a6e5e14e3497a897b23462534b687 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4915d5479dc79943a1a38b023147b48fd7a33e23b602a76d2873a8826e04cc7d +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6f9c29bcae7d6c4c0b34a92563db409c26657be --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b75555cd90d231695bc640449b3fda8b8fa00d4ed7c9adffe059533aab21af +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f53eda9fb124065e4a8c334aef92614fa1edac4b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e3251c1476824d6cc6e0848c8b26f5ba1f863e3787362fa45e0b61e14c0222 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..502c7d0096a7ac03dcfa5039bbe06c56032ec64d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9737c8f412449098e31a8ee26b4779677faefd16dddb857599c5c8bca07104d3 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3303fac362f4e4fd92bf754f37aa18b0ad9cd304 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da76a525b81906b1bab5b5b8c7a10615589c111df8bc335979eaf95abeca7a0 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5201d4126829eb2e7b24c0ccc4446337522e03fe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7aba605edc7b2444acd9393a76cf18e088b77bbe1be4d3fe2a4010f2dd00024 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da98bf5147c4d47109894d51e717d7e1837cc19b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d2f240c82a20bcec2893e0b561a7424eba0f6418923537f934a54fb2ecd424e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..345d4e8b62f7963e49444be0fab685d62b786ea5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949e79ad4a1e6bcb761b2b7ef80660f0ac6b238ff4b9445e3c890c2e52b9d258 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc32cd004cc2f86eb16c21a0757cfa72f1f7bd82 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df4bba5f0bf1ebacbcd07a4be0f669a6be323e2ffa0d9510641a0521375293a +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e767656cd4db00f8dbabed92716d29b1062852c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9713e3fe5346f8e175ff95e724c929b6c67ebcc52594f8ac089e445953a48d2 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78758ca7651acf488ce81ff5161882f476c10616 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cbb294315396fc9894d6a2aa67e1494e6e33fbcddd3a73a6c8352213204e1c6 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d2091cb036473a516efbcb5255486ddd0bcbad6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84b15b7ca0d15c3084203e17915f9965aceef58775c6f1ca4f37e07a464d4b6 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d1ce9ce11266731247d58ee4d931bb1d689afae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e17c48ba777eeea0a516e7cd51e8635c1e2c7ae8ba9e1ee365a8a3b641994d +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b23b34c83c38cd54755705ca85b59531bae142c0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6797696cc98832eacc336ec2bd0d606114771157fe879f86facb243a8745d9e4 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..500ce3dd61d9db96828e26829555d0c14a00e662 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5843f39d0c9234b1bdabbb6b11346075dfbc6c28d625523a6c01b033988a922e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..09daf020e32bed5fae33b42be82e9fe34c9d3fe4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eedfd8129477c237f6d26bda608862851e809285434072579873d917371ebbb5 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e270f5c96142db6de20315283c2df32f9801f6f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7934435837ba18dfb753dc3d6a98d64cc104d43490844404763abad309b93a8 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1fa838ad005f74ef32553781397ffb26640f23f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f0202b15e38edb9d466fa1893021bfde59bafbcd6720f1e6aa3078232e56f3 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9006ea1c81ec4c5aed1bb2f6cc925502a0fa9fd4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e813e149dfe3ce4d02560f036a9ff41408230402cf7c410ed3ced1d640940a17 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d16084a86928b24de0dc961ac42fef0b68c4425c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610a431dec4aadd6c31dfa85c1c28cd0836908c2a5bae1dc9b047b6759d94dca +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6272e281752c5acca52f12acca4875649b0fa0d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e72e99d21ce6f7f937fb1a5f3b6ba0e40428ad984b21b4d9c5497f45690cf1f +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7381696748bfa5efbec57f2bf9f366dc710e0a5b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2a3e29948d0394b046b468d40b3b39c879a1e7d40ca6c682ff20b3e2eed9dc5 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abbc526ca5cfae98bbfb35d8aa7b06836f0f200a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b596ab342b8e586efdc3058c7865d322d32dd087a6e7bd0ab22f6a0e268c70 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19deb42e108b90f479f53bfd49f4bc30bff18f59 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53db5e9f6479cb189e6091b345f4221782bf9e4a77ca608d7a7168c8a2a8533 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..346e40d6fd717068ec22a7ce2167834c61ac8f77 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579cdf9cf813ae4a8df0885523aec83283bf9e78888842a8feea62cfa3cc2389 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea316657e2fe77a2a68e139150adc596991c4565 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d0f498131593e8f5df7774290893d027cbd5b901021739eaa08f26a91489e5 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5255ffb2459a9a6c4e53dfde9502e97b07ad1b87 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544d31f69add502faede3e192e92f939ae081edc3a6ee507a94884f039a678e9 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c32e96a340dae538500b14e177c24920eb7fa9a6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5785eebc66ba1a4f40e3ec12d8cc2d701d5879ce01dcc57492f221683cf6f53 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6635a11c22121a854ee8c0cd02bccb26f2250260 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fad770207bd545bd1bf9d754530fc1019f1852274f5501aff515c928fe44d2 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da7e97edd7cdc6de3bffaa263792c1d3660bccd0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c418c109958388dbd1946508c7bd2789dc565cd16a576c85d2e4bf8e6b16b1 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df896c52c22aa8792e8662056762196e5b6a07b0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6e690f4a289f0e0c73da5928c63bbeb5e203f0d78dd892f6f41f1923b92138 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad0ea282f872805add10ad89d142439592a4a0e0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:522324911d86564cb7f4cfe07fa8fc2ba183dfd0cf38f66ee917d3a663186987 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac2def609187b82365265376032fd5f09a8e5fe2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152023d826513a078c736710292878a04a1c2512e9ed021ba1e5e31a0b37b588 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..86797351a5454c0615c417e5b3e9709c6b935e24 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e5dd162d918c73a1f5d23e0e78963de768e2220012a9b988750af91b7d4f89 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..12bcb87208162b5a8f1f9278bec15b3ba225f484 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e080d927102cd65cc5ab633c1610660fd653d18175c3af79614f3f4635b312aa +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8db9192eeb6be82f31a62d49759128396aad405 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0148cf6bac8f271f584a7a309c8345abc1aabb3ea892e663241a75d75ae470eb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b400a55f9253a4ceda2c9f9ece50da89ae16ec3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ffa617604aa32c1204ad4fd47a436f257cbf840ba47616cd8db25daf4612652 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f9769140ed56fd04589690b51e4a930f8c80fb5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b9c277054b41899f21162a99f37f57c7c758a6683a8dca7298382733fa54334 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb204e94fe60e3fdcdb1e32b63d501dd04896fec --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3ed7081f4749ab8eaba0f6f05034fd97a858cb479be3bfbc70ff9c3f7d77bb +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76dbae1e5a2e2023f7a22e8183273a1abd6cba62 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d3d428b1d4ef78295df85d4882e2ef906a12a035887a1c3f726625b3281b82b +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a50a55de0a5b038e8433444687b9605374e8825 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2245fe9abbf1aaf57ea8193388bead110a75e7d0aeed71b26cc557e81173ab +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4afe2105fcbf6f0c458a8717207000ee1c1a158 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97fce5997edc600fd303429be36bb96287fba94d7437f08f441453cc8fc71c60 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..47152eedfdbb909f1e0f4508aacf72e97552870d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3edfd27bd0951b725d677999520457375f3955bf1464ebb7e6639d30220888c6 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a763c9fe8c5848d4f9275c36ec987301f6a87ebe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb20fdda60a1eb9e0e81e89e22644fa522abfdd43a6aec28de5ab326ec806db +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ae4d96ed827d12f734ea4647c4ed09b2a56c6aa --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa74ccbe4d6569505dbf9eb1d92d2735dd88d30b2e56d6673b5fd3f7bc7cb83 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36cbc05fd7f26b30761273c0e7c7d63b860af081 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d55b301b29cc23a7c72ec30991b19c25611412a49c4ef01f6d32b28fd324c1 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1e47c69384417e96c7e4c37fc9f5daa5a6ea185 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b0021aa65896a1053a5b5132e9275cb4a4be476e3dc800a4ac2f3c4f42e9da +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..240208cb59ea22fa4631973c6b666cda15b2d312 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29314cce00015e31b7518a53b943e49c0d37f1dd82c2e7a0b1aad3625c1c71a +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..550c1b7fd64042ce9e400dff31056de77601a99a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e0a21073459653a6465f0182d54449acab88647a630733c96124dd7e1c64c5 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6c89d31f04019e1948c02e2c32c2c8ca446b9eb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535d3f7ba9ee3944dffbd89de9f5dd4406a13f161b56153f67fa0f8f76896453 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c338a3d90f1bc866b1e32828053f62d8c0667418 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec1735c1edcba21c72d701b5067673b4411d65061a1cc1ec11910c33a1db3f8 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f79c4bb822ab59ba5271278fc2e417aeaaf5f61 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a25aa1b2020ab8d30d16def6305397dac2cb073dca89f9edace02169c8c916d +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77b5dfe6e0d7f2dc3d79125916674128b84cd2be --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e89c16fd74de28aa97d0377851509adc13c3ce5773ffb5f524adcb255ed5d7 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1c11878cedb35b007ffb85e33dafc3d3a953369 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea6c7122caf2866e013a345627f56417c3c1eb389b459808b251b64e1d1f54a +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..570e5696e1e9a9de82e277fe22ebe65f5ac0f138 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d75695c9d41f7a10fa522d3bfab7514881cf679f20942197b1eb0d60b4a02e0 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76dd923fbab22f7e3485d8b1a30073b69f151985 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61e37992cb3e1ea5494f3d7a2178610dce147d1cfdad6b4aa1bca37b00f0aea +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd370d2e15bee519352b85a1662bf97c46739021 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a7e97c2c52cbce792086e2d137ec2b0d8e5c848bdae5d9e0677a63b5443e53 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f965d78237dc8f72b465dd0c02cd83b695f3f6b0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f13f0358615a0ea5772ae9dca469d0a2e8bfa15e709b0fead0789a7bf0b43d4 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c68eb669e36ab2dab19646332464f4dbfc9544eb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8814a14bdcc95474d5f459b6468b849cc7a6237dfe64d69ddc7f4eda32de19 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7702276c9c7f0d27d9c3471f244565fa5afb8f42 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b556712cebc37e0967dd1ff8c89df2fda51f3568e78a01370163c5e0b322f5 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..832d46c927766e2d17b8bc9ccc0de71860c13df3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9010362bc277843a524b678133e468c633589473c5d6d56b8f354418aabc0f01 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34e154be1fed980a805896df8ea17db03a216318 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f2fddaca9f21b343aeeb5708ef642e1cfca363ec71cce1e1ce06c27b7dfb42 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb7d21a4a435c1f723839c52719abdb081def13b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49452264fde2c7068f6b88582f0813ff16207820a430f3942b6d447cf6194eff +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4ab3be1bcd01db59c12a5e5fb715d231d6a1330 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041baf884eb40a85d8c9790ba15632c4edc0753a5bd9e72892ce1f7e52db2546 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..147532bbbd8074a98c10b078471836bf1586a99a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98cb8c9779f417e7b5fc329814022f8b2a39508c6be30d5fd5c0c1841d713c6 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3eefcce6955bc079ab6ef623aa91a8e6f7725613 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2cf6ff11453525d90027a548e68ee39608c6c0982e5bbaf726fb9d89ea33bf1 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d80c1b598f76dd3187555253e5e7622c637dc662 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe33caf303511687c226ec1b0496edae29aedd87298f467de42b7f05bda2f2c1 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6f6547ae5f8f461409077a9f4a6a8281d092f8e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23c0cf96f2f72b848b30a2e568628aefff1f549866e10c733e4346b1fec526a +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08b67197efd5df941585f7685722665a19ed1bfd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c906f5247f5561e03f44d6b1cf28e3f46c1c79466787124f3ea387a3b97abf +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7fe8d218a95d8a501013019179516701a0d541b2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412ea840ee1e9b21ae87126a0b321d9f98f6cdf225a6d3b81d4ba16cb310c7ed +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..693acdc7bf8083d144ae2a1d39e453769177f5c1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c4ffff749b16bc31acb393ccfb00c2719875276e42b665159a8e5ce401ed99 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..177f011a85d6972e182d9485109391df8769ffdf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d39dcfefc638945548eef80eb01f4289eed37cea4f2d2f7b8e5bb52c622c08 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b2e9ba6a2d0eda4db6932c9e8cdabfb8843c28e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa632a215e82f731272f142a4d08d662b3b9318508d9f15a3698b06e621f34d +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2480098276b8ac4881590b1515e366f196c072da --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1350335247a46788ada9b9190d5b135daf00acee0f7192b420f018e9af334cdb +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ebb475bea6416514775e4ba3311750061e35ec9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7a236711ae07683606e1311e1d0963185d4246c006ee7c568ace75fda08f93 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb3ae0a4196740b8207d51c0e6f536fd7299fb93 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5e40cb8c35a37b3bf360e5e26a42964c2672c9e39f9f90275db239084f682b +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f915d4cedd741c87032ddc3cb0645a66e8ae54d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33fb9e11a79b0ba0da0c5073c2cb90041f5bcb6ec9490112305bd9519ba8d7c2 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a67180954a9f6df53110a4ef21e6e5148ffc8d94 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2285abfecb7ce82a258e5ad59913bae9585ec79bebded821f99b255fccdc8519 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51195d6467c34aec017da5cf5b8e32998ac4b2c8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b0864ed8a02a849bb1fe9d40f5bdd65ce4bd2ebc1b278d557753e22c95d92c +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..95f54bdc2ca87c5068c9f4c0af77541e36b18149 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348b7812f9759bd92cf4672907a18b26343d524c08d5da3089e1fbedb21fd86d +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6054eaab8bec37f8a4a8cc498601d4ba7111f136 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012e97d45fd66cadeb414e4b282db13b72d7ace99dc5fc1fa16bf14c433a9189 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4e77a08aaad70d7a53dde3835b5d7e858052d10 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7a44b5a81eae5190f42809d489728401ceb1030ad7c6044cd3923b942f701a +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cc7021ff8d1b7bc691abf0730982e08895b8684 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df51616f28b2bfd4dea1ac832bbe78c251f6bec31e00da273699e99897e5934b +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92fbf03beae6f822dbe69c8ccb1f202333f8673a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b02ab7c0b597f2554dcef5c5c2b272422579618bfb67cb0541ad3f5d437b460 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..199e6eba040397def716573da0e7f33638a04a6c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62533e317ccace3926ae4ba872369db19dab83958cf4f42fc9b64d0cfd8ac4bf +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d125a85471c1d19ec4046538d39b51abe8f3111 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba769734a2c4002b82f5a9a6f3cc2c6f46c771e9ba975939f1dc553a8c6e133 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b12fafb6c2bdfcdb8f50003acffa02f2bf59779 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0cca9d35f88220cae8b61024419d3e86e7a8e1bae0f1a9347f4b6e978a60d58 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d218d4ce966411e1caa50ee8bcce4f332ab1888e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85cfdc721599a6ee08480e1bf2485c6f1040f235bda464bacb0c76e5ee7d9eb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aea7ddf0228113becd9c216bd8742b0896a22ad --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b08b6d4f6849dee8b6e83044db55847081100e876b2aaf9192fe15ff001ce03 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..378570fe87a4fa6c076da9480482af48191325b9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc43c9b85b8133a2ea1e0d78caf4c533b0bef60830381884cfc5aee7d80fcc70 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce0e76e38870180fb3734256ec94b53add63299f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4fde6034ad83818d396812c42a4f95264979f6ce03f6934cfcc8a52d7af965 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1481345575757f40bed6b2d68464dc84c1f57d37 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebea7d655451eef3690a1fed6fdf01922a2f852ea332d8624e5da6429de2c0cf +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac1c89e16a6f64cea62e72cd5d7a6fcf72acae84 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1d169527a8e1d7f5c20b728f4047a0fc7dd593df803c5f7945d19c5c287cda +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fbe9defe3fc1b140b3ea3d03c03d4a3cd9ec6b3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:156d701bbe150802699bc7cbb6353b93f8fdc629b74000f65242179307dace27 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9157e8003e8a8f5419c54f87b172c28b5deb71c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9632f8ec64ced301e162eaf28938ec7e3c7b002fed8f3dc235cd671ef7c55493 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b57d8acf26106cc9c7e6e3c8799cbd6dfe9bbbd7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc28592822e47062f7a1ecbe1c4e61595d2ba4bae2880c20354bed35ad5e882 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e60b0f895914fbb48d54afb99519851ef4b9bed --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3aee9c87d432b402ea6c34a069b4da3a3c1ff25725a4cdc9db272657ec4b39c +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df2c836baba483bb7807818d93987f81ba0dcfcd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c841676550ca90e87ab80236bccdbba9504e6293633f7558d04453889deb5c +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b55bf046e28714fe376278aee41ce685462b32c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55801236e6dec6819e452a9b1fd8945a2bc7a0c3f5bef3fa18afcacc6f1a85d8 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bba8460a1aa19b04d640e6d7d2b123583c65c28d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe03157842f31066761c5c7efe4ad48d2505e79d2080e4a95c2531a48fc4dbf +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0b0a4a1114ec42d791ec8d25372cdc76c57031a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a4666081dae60bc933affdfcc5f3c0ee15fffb46ff5650dd138210309ee352 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53fae4105f2fd99f94fa25dc7715bc004bef828e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c418afb1b0665c0f25e50d31c25cdf34d3a83786cde17178fa955be6a8979d02 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..777eba3b4f24e8f39b7cad85e5f964d6e415f2fb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a75e53c3ad17d8b10ff0e47422e9e0a2329e4758ebd95f70c7049662d5b2b2 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5119f9d2137a3c96ac040458f61bc19fd16f3d3a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d624eab275825baa6281de23a1a7f83b55cc01014597f38d49edf0f654574db +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54adbf2b75d0c9d9394f71bb0e7a45db4123a66e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9eebc30846cdba4a1efb9cfed7ef660eccd1274a3ccc68ea9f42e374e7a8a51 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..47513bf1b4c214ce24ca7fac3ffdddf52fe83329 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c774b7c1382d6968846ea41036890d2cc3801b00d92f400c492bbcbed32fa850 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87a31b21c9ee56c0b2836ccc798554ed079dc520 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ca86433f906dcd55ca6807ff6f8f2d0d5eaffbb1b09d73164ca662fe387dd6 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98121bab55c648be78ce1386327881774d0b1143 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e06c9c77d123654278b7581592b2a25e2546e8f8d68dc77776979e72fc8af01 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbd2da8a5ede4f3385a2118bbafe8d0fc9c62b8b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3b29c704bffec448ccfb5cdd794aef25b262b30e6ec5e5526e40235c9b4b42 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8fee927298966bb1be0136a5814ecdfedebf466b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e622885a0dd50d8a714dace9c87044ca4bd3013a8b8b09d68c9ab25a7b013b96 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa729564a49077f40e9d7cf30576701ae562a446 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f2b626595dc8877e0d76bcb7fe663de62a9eef0da795b70e45132ea3f93320 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa028e41628384da94562f53b1a2072994b19675 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f095d96c1b08ec007d464d47463e9cc68b529d37d53fae324fb884b0667cb8df +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a098d8042eabac758a83495bf045477b257d882 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60224140335a66c50117e2ca6256fd5739ff01d7308db496dffe625f0686d076 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7af5e34284663259e8e829fc8b2ef62bb0ec3301 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b63eab6f8f1254dfb4d3924b46b6d5a87016cbcd1d6e8d511a56ad36a2bee6a +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6dd6bf56cbe54c4cf88bc589fdb9d57a4fe3d33 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0fb3c0614d5820336e9468137eff7a7be3b9de2a99c6b3de2417a4bccc6e23 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa99365a692925db4f50d1085e954517bdf746e6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9900cbe741ab2820fcb974292eb811c08c1070d498a4e959337bf64c614e04 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c34da168bf89da18156bf817dcb87de2fa969e6d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcffcda3bb53eb9bb4a4cf36cba18cf1956c4968539326854f5a0f8fe358711e +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29e3f582cad71d9f15606ff5747993e0e47cc53a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01b71faeaba39313508571c17f1d0efaa709238fe506d639c904955a68124a3 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e935d2fd398ab707040be2e543215e1da1d9487c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e14372da3dd8c68d68aca3c2daabe7635f52478260d77cd45c95cf4f86d0522 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aa6bfb329792382f453dac1e0d87454b3f16830 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af0b4078e100edbd6560b2c18677cae3edcff1d69dcad3c748bc78172708efd +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..870208e422a84ef3740a21435409b66a7ead96f2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80997d5cb6d8bf2426caa813b06864ce0f814bb183a7493b8f3852cce7bb9da8 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..82e4b0669299547ff4e86ce7e2e12ea549fefa68 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032d983c32e3176dd0b758f2dde155a9802add24c5ee9c09bc4b331a9505a232 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0b179d965dba3ff14d41ab42cc0f9e16a074570 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:689798768d3e613bcdcc626a6ff3bf6859677178f5fb5614a8bafb8ec88a6817 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2532091233aeca6a9170d5de723f0348aaf9b4b1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3775d652f4833e1748a28f5fc5feb0816a25d020def810037a240e9c24739a0c +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..56f4b1b310842891bd9accb0acb9221a85139309 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5540bcda87e9770fd8fa6b98f3b4b3d739494b58fa6a6b844b45c41bca0379a3 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3805cc20e5c30030d90f93e882bcd584f6c5e5e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643a1b7abd8b085ffe4a252a6b592437d6eb8af19a34b36577076933ddda0b27 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9a9d2e205bfdd82771d3d74dd627975bad380b8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32725df69fce0a63626515f4e8163efa47efa38c6a8cc6dfcb815e9e1df52c58 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..679ca241a74c53dd9ec6c94312e383af54772d4f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3fd06651a6c8cd9f93fd1e72f2038e1afd909e1f589b97de413d524d2f21406 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c9195adfdbbcd2ca3accbe6344cec7b7241a9b9c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4277535afbdfe346871629ec6f3c132ed4ab8e660ecee01ba355e2d66c7fe5 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b31d3d510bfa7dab0ae023e0f6dcf14c530ef91f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25615314b216076e81f52dd807ea448453442d5b00c1743c8619cfcf77dc806 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1042d03a482866721e9865be4c3c37ab0b3a14c0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0397a86e818c9b99be4172ba66d81b75857a3dc7058d361f501d01e8317cf16e +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..991e7d44e3d38e17f24e6c22dcc82da2780a6bf3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e063e05ec341bc4e12eb8b29694c2df94754c6ea1664e8ecef865b1d2e0a1abb +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c17a9998da8a45f4ec63fa96c2d977f5db768da --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26cfd7342fb58a1f12148c89fa1da6f54a377248b9ce21065770030f44fc870 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbc80ba9a300c1b02ffb713713c852959a722692 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5505a788da05901a94878e477330cd8068cd6e2830f8c6a2a4701a7f5b4a7d +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..037eece39e254997b5261f42d7d48959b4b8bcc2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f704cf548f00a26635749fa621562fb928b0648c144da7ec88c2932fff6ad72 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87c97f45bd5841e387e1df43e4a99c341843d08b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee24be903ed65ea06047c58bc69f25f61f4b0c5d19aae359a7aaead255023e6 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9003c384bf442ba1cf3b61c3dda7189dd7004978 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df76801a07696cd1d1997014a7b7b247c0eef0ca16dc5f9fbf09fb413a812a02 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b7b5efe894f33a32a93bc7258c8f63cb3247314 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54e1f86d4afa368c77833591fe71faa17f59312d5f24d3536903710884ce873 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db7069f13bf4c890908946ac4c0e44532571e674 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a70d4d075afff4eedd0223bfbf0019557ac811ada94b4b3d35715e55d6fdd6d1 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84a387ff653501b55b629721763808a81e677f32 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b9857cdf039e8d10c462ebb0876fae00414a864aee5eb8524c6eade4436f8d +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..445e5fc703fa0d43161dd2cd0e7370fb327874b3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45cc739992616025d601c5dfbd49b3a83708296c0a659bbcad25ea03dfb1eee +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b28661484506e67164f26f1165a7d45315769f4e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f464f975d06db9c0022844b9c8e8941d2bf1c88f342f1169d8482051e78d1d4 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8245d57f29f6c3b382446fe4199a1fc3135ffb3c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b924354bde430a28897423b303716953381c594f470948a494b87e003050b3f0 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..472c80161d05757a22575667d50ad3c332c9a67e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46dde86263c1c2dfd06ff24e19267d96388b2bef483dddf88319fe0da176acf +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dc6dd77c868d7612b9453247df85493e1287daf --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef296b216bf2d7b253ff0570f45b8677c300026a9ec2220d3a3b7514eb5fed6 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a9ac013285af53ce92b399fe6072494e6ecc3e9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d5ced3cfdccf8dd07fba8805316cc56e6a305bdc4c6c69bf7bc576eb89d50c +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b460ed0bfccc9a0ea8ceb3e1970001929ff3ea6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3edf2409d0ad9dc05d40edf895664c0209ce79ade86632c4b178301598287389 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92be302536654f98cb912d4e28864e68e62fbc2c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23ec05e80fdf18b382831e80e2c780db781eb8a52eebd4675d16b657ba3e695 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..252430fbac8834af28bd80c31a63dcba096ab534 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86438fc2ef0a92f4d7e8c758650a7dfdfb1b93a3a7dd71b8e47f27a21ac43dbc +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2eaec2adf86b0050be8339ab892e9bc43ac09a77 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e2233677dc78c384e83d644c9aa61efad6723465da3a6d71e1f17a62f5021a +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..271741daf00a262bf102fc591d304e21e14ed665 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4696e79c23f7529fd8b2dad0edd4b2baade1cfdabfdce56f31eace5e1905fe +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..135fc310cdbe392f029d155c129ae0dabea41f6c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3b3d7b0c5c9fecfc7bfae603ebd71d668579edee40774152de48770879b785 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8852af048ed2bbb0263fff7c87e3784b0fb169c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba8b3a3c15e77096d263ca3f709ccd2b0532adaa92a765ecf3be709d20f787e +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0a4e3d8b0dd3d0929f79a8e21dc0edb9b02b89c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6e70247cd81aaa532c7bfa1119a0966a80b269b08fda0a39e6c541e85c3580 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57300924a2b32bbf614f9d7061bdf34516b6a89e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadb86a32c0d5117fe6f4b81515bbc5a79d3a09579dcb34d363a9ea870aa62ec +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f98993d2078c270b6b8f1339cdfaaf43f17811d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d905f2dc6ecf13f91ee7d35a8075de6a87193b236beea736bb90585b45bb0f +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d61175d93b0cac0cca1042446a96f73fc209ee26 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf6ce9dd61fd8eecf3e367dfe0b1aeb7189564aa15c68fac00d3bddbdbfb371 +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0dff9752958ea15201bd38dbb2d4adf49792ffdc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b316a55fdbd33f53ddc6486862bdd9bcaa05f520abbdc36723d8070104d9e551 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..11d7a8f2ff4fc55fbd43d51f1ca4351e08f6b62c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf69097a3cb014286105fea7a4c0b707db21c54f33fa6f39b977c710ff91feb +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d0b6bf1692d7af79fbc052bbe17ddda85fcc5cc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9db4a3f3a85e34f489415ae42d6eff4215f68cf571b35984cbb57d5ee87a38 +size 95016173 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c02b09ba0da1056a1b6d1c74754c1c539ac0ec9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa3f81c946f8473b8e17516b1b3648baa65cb299c78a467c11c8762d9d64c5f +size 95016557 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..927e023dbd54654bd5e1dd06aef5bb143e65e9bc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5a323a157629ebffe96aaeac1d5d1b7d73360af76437103187817e18c1f47c +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e3c80fe0ff594c4b638fce2f43465475fa1441a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b5e76ee258efb0e018461703adca63668ac35406a81871da829935bda8cffe +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..13216316a9fd3ca75a8fa20e89cc02972721e888 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4775fd038d1e574943b78a27278a99e20bd06624a7bb6e9638fd60ed4dc749e +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6654fcb9c40244977d693324251b82ace8b54927 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b30ab3e8193a34eff99178ca08f45986e9ca6ad0ca2c5f2061b6950b51d149 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..69e85925ce1de604e6e63eabb6e88fe628c5093a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be8bf77b06ba0a7b6211abb784d993de15b068e8c2ee354e99151df48092003 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81185c40a393c4ca19575fd29fc121925f11ce2a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38200c3d7333a7d436f40c44d85f0c881ee8cf13902a82c490be336983b81202 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..baaf5c1d64236d5a24b4a4b9c9d87b76cae43345 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0d03600dbe4f7f1d9c360df9c85dc5b6e12ce024999aad4814aaf0a6f9c4e3 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6e6ca296e127616efbb936ccc408adea53d56c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5837c2e2df90dcc221c8e42b6aa08ae2ffb291531e3f4f7f17c88e5e6de1ca74 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..48a6adf00b5f4218e60719d24f326257976eeb3a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0bd74e74879ea8085d3d8f66087e36d0aad080344e8a73442a41de653256dfc +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dad640d2849b175b219caae2bd83050b7ec8350e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cc9d5307a078a8f6edd280fb91217753a0df349c54194ab482ff638a05f438 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..af51f894ae10a2829f10ac3aff22ae451efdcb50 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5738f5a413a4187d031ff12227ff3c62c474588dfe29788f034437ac94abb0a5 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..212042f9fd343ff06bc91e5c7b4f96a0aceb02db --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa39be798e4547a08ab79945a435a70b0bf7605299148da2fe01fec24291c37 +size 95016493 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..68785ef32f2d126981b60c4709d68747877e10e6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e7a04ac912bf6800f54efa7e76a560d3a470c69584583ff274dd1beb7136d9 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bebd50419065f04b923c9611437b48f1a53c9743 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e8a62436d9b411108bb3717a094181658305cb77b966b95d814084ffe3dc62 +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..304adf5cf53dddc975e78c2c793d66db5e5d5ae0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d261b9b69a0a19b981d6f7b2494d4c0bacd0afe44edfc4e5fff03df5dd7cd4 +size 95016109 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..871f87d29601e3f58eed68d7a2e664b5d08475b6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd011385a1b46b5634eb446a16ce69f0b570bf6fbaae142a3f7519f497cb3b2f +size 95016429 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e46d14d2345b0decd481826a3ae02808a22fa284 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ca231ceaccc9b866dbda5adf5e05569de71c3fc9205af758336fb4a7cb2866 +size 95016045 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04f16f82072938bfaa31c4c996d20ac7760f233d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3969b70d10d2943a7c6a430e1e05d1d62c31231cdf2df13ce79b7ac9146dc24 +size 95016365 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..99c51367f6d79f32d0d7e449d021bdb23727f6ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e74acf3c341259af5fafd267384ed687f50d242a1d95b42b86598af24d1e417 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b0459829760b52a0e2b8951add000ed06292230 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301f95ecbd2ed53e3acb38c7bd2ac879e3d5eb83714a66e030a0eee6e94cb197 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..595a417c22243fc25f2068b6f3b42820eeabfad9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb0a26497a30967b938489bb754b095570fa0768a0d252b787da35d4c5e6082 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..14f1e784f9aad7bb75d28aad8b04d3c7028fe452 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e8d85eb1794809c36904367570a81fdad0de49c0cafcd8413d2f0a3eb84823 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ce6b6aae8753023afc121e9b5c1d7cf9914c4c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4490ed915e8704d590dafba887d9c95e934047deb00d340e2e34ff6b8a10efe +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2084c0984df50be78a7db691116b65fb442d5902 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a424997861a7e8b6c57335022bd78aebe78825727e96f569402bd2536c5c33 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..359735b1b537f6c1650f5bf1625c816238fdebf7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b118db818ff747013bf7958a0bc47b07f4ffd609dc7b5031e1913de552d0a00e +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dfa34056da5bd6679d6ff21965801f281397f22 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882a82803e15ba771bd6dd5ac4ba38a928a021c9b43663b04c83ada86d8a6f85 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6640d16a07b7c659d67f535f69c2cd0ae98e4d67 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e5a919d9df3570f347c4552942bf1120249b8c8d587b204c196de647a0ada6 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3dcd98fbfc8470b7afdd5c4772becbcd88e5e20 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f2b986611305d717d9737ae60665cbde85a70af0d90cd16ff048cc15908f4d6 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..818baebaabca6f0ad34ba11a4ac39a6b0785532c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6742e336749f8159cd99d6f5f3f8e93a09423a848b68699fa1cbfa2ec98ac50 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19d08539c78f338f0a98f33db5bb3b32bbc68e6f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b7779e99a763156567668ea501cc8098dc49fcd60a905f9d2201ef41574e06 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..960bd3049eb664f05f71dfe78dc86fee959e9bc7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2fc5866792790e2bd21764baa83c856ac359240b652566280a9354adc47f71 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae9febb7fac067a4c8f2f8b322ed2e319b022c38 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f1d9ce82108f9afeb45329d394c8b4927a98dc6ab6c32be8dbdf2036f34e7a +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a35876293b6156dc839ff85a7fbc98c47e592816 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee028d8a37f1736d1952bc0e7732ddd534dd271b6b740cee91850f34e5dda183 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..18396c23c5934a0f1eced85b081122ecdcb39d09 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28bed82705efd09688b70c48b9073474a6c33b42e0c2974c203f1705e247df7a +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d8d9931e741d50950dda50baae095b7b1d02518 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895aafd4d91401dcc7320e06d4f3e6ab10a0fa2fe53faff77258ad44a7b5eaaa +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3db5b44700560c7a48b6a7e00ed6faba1aaf699c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563c40cdfe7b319fbd69b716e1c8f315dbe0bcf310e7f294868e89b079b0df4e +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ec04135088691399e874b440967d5b9d3da2e21 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08d05465f5616d8ce6cd16042d6b5cef1e1cc54a1d6f27e97686dcf44b3fc77 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..acb7d1ba1497040c4f871203ba11c45870173f25 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f61182f80db931132d2de80a6ee4ae10bc87bbb5d9341dea1932a211425ba3 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a96ede400620cd9f89ac2f83b9ccd78b63c28a7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cfb0d05436ccfd4306e504afc835e4c1638667fb034b62c9a140315cd823678 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a79f6d7eaf6135aff5bce7a5c0796864ef7ac27 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abeb039117868ed7bfe0679e8eaa05e4321d9acae85f6e4400fb63b8c8eb3836 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd891d71bae164193279b82235bf3851333f2bfe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab8dea4ed70bc62755110433bd379766bd42de9f13b1f743de04b693d4bba00 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ca4625eda9652d39f8728c8d27fe218761c93cc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413458c849a77058b3c7f9981b96bcc9b7f34496355ade16c9b86f96b541da1d +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c619c7cfd0f6642308ed4c46f47b2667df85eb51 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f39a7f3eae4c9d1ae0d75dc1359831d8cdfca3f8846b3225dfb02a97ed6a64 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6cc68cfd0fda32d6afda6de6edcfe8a7760308b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36753f554612335384e705351b51cae22bf5bc7375b0fd62d5375338342cdac7 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16763f42d288896d10cf664dec6893fe348f4bd6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12cf97f351f0c4573fb9659325ce3320bd499e2708cc22a216e53c5df6b8b4b +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db153489f1e7218acffc0a5f1f617f209d31a6c0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3270c9703d4ae84e0c31da89856c3fddc203d881388abf094417262dbd4de0 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..48c20477618c12c6eb6e53b24dfc8e83c3d53853 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd7531bb2161c0fcc2bb998c06624360671b74ddcaed710cd8dcba30cf4789e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..21cf54fd4002a779056c5aee3ef8a562d7142fa5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474ae9e0c9213a556610b78b33abe574dfae58f4f81e50ba28997bdf0803682d +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..68de69e9721a9d8f31cae29dfc9140fe9a647c0f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39fb65672b05d6be3154d1527cf4e04879eafbc7c99bd273f81e4a1b0f9a304d +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a827308abe23b4f54f80f9cd313921049233e6a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d214d99e028a000dc9c17cbb4c5d5016c2178c7b30df8f79cc1a2e4150f2801 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17f00259cf3969a9b987303c64cdf061c7757ff0 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9155a5c5e089721c95809dd3e9f6b37410493c462aa4ddca6715abb4753ca116 +size 95016023 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ac785a87e6fd3e3e4f780ff9d44401020f21ea6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68cff61af512c56ad6fc79aa406486ecd7d9950c98b2e63ffcd876fa308ec770 +size 95016407 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a9f27c7e22033e3a10e6e53c9086bbfe187da1f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9e432e472d8cb3c1b8aa1c690ba58a6a3f83f751c4ac403ef68162d14cb987 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee6d6edf306859be8013ab5f96f47e93115a2c8f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f958569c5814b4c7e2a645988d289c1c00fefc263fc8dc99a26dd994dbd6e57 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8049634d482bd348fae0df00e694302934ebfceb --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d320f26b29fe015ea5c327304f5fec326a29bd73375eaddc9220d5a363b17026 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a788933e5fe301657384a71893728daef07dd13 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14712c3b69b58d9ce971ef53418f1b93500ec5cd784131a206b811915cef833 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..91dc989917f3318042cc7aa0e1898d21dfe4d455 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c4ed1200db8428796bd8e8dba76380eda3f156656edb88a33be23bb9fa756e +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2727b416eecb90a89376b0829d35e2af5b92ba8d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878ced5c22bb63612e7a29224865cb010718de385b537b5c12fb452bd0bd7286 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..37eb579c9732d9a5b73c18e2afced64c2daa52a1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ebae1308ba70230c8e7f9ac04ec13d4e74551c4348fa6b7b92e8187b64954c +size 95016226 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49762f7fe137e873cf2b5a68f596af600ce23982 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0852daa4d152d6af213df46fd3fb82762b6ab10cc4f9fdf3a41dabc6c5c4930d +size 95016610 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3bd8962ee65e752c5d29796cfb00ca591e34e03 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da880191afbd6904eb034eeefb784dd9a1b8179d82ee4aa861f1b4a3ace838f0 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..289c15b59bdfbdd4f309eab7d46f944eda910b12 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d728f11fd6456d6c44e3c97db18981649225c8cb1d9ee7d79fd8ecb1f1d37c0 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..82830178fd82823928fec49980aaa44a3bf197f8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6762b52b01db48b6271d05e45961abd6b3c6510278afa43f1583e9635d50c1 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6751733b4fc5d10f891660e9db8dabd6feb60899 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c1c9c5bc67d3939e0e2df0ed6bcb0e63fc502692d73a7569891b5ea2c0ca8d +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd87280cb619c2ea22b11c7d7dd1da3afcfe85a7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d688c44b195349ad27e501663ecf2e50d61abe252e115cd63d1a9f85270e8694 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b2c2e4f3e52c4c9a3b532f69626447fcf3988e76 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bc564f2d556fe89fb71206f052bd3758e7eec4ca1dd5cc7bc1751cb361c2e7 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e628796959e09a5f1463b58fcaaa8fcb4624f80 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0df6ec56b018dddd5be788fd98ed4547efaa8bfbcfdd47686a911a4edce68e7 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..878840782ee49f774ed0e0104bc7af7600cb66e4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b596cc9c634aa1f9c73dfc8a1f5a02acf24dc9c8061330833ff2cdaccf9f7eab +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..55a7e1dac01ec58c57bdb7cbb132589d46503c13 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731e0131ed36514c05ed3f674f02371af1549a962aa4fd247f33a7585ac78aa5 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c02edf573f0ca1030e7be0173a8c67206be0953 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e520d06830950fa9f9ecff9bedb5a6e26c8af8b68118592ec5d5bde31ddf5f6 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..852a1983ced40255bab67f12665ebe29964d4ed8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee6a28e2aa6ea2c881519eff3aea6819bc4bd9b2a06106e506d108d77d73f8f +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b07a42d311d6c8e244a47242e006d6ab236acd48 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72862d73f52e65e5ba3b6f3a0e56a6d21ef443a0b1d8237442a869a8ac741b48 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2eba4268405d6286bda1d9cd1f5049a48cf0c81 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7c6f468ad8b45eec9008d923e5fe2498f4965457e0ce08d5078cf65b960be1 +size 95016023 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3b038e1b5be34b1bb40952503e71eb78bff3f6d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce215715a45f38126eb5df4d274b8c8831ae35214fc425ef115232526cc5c481 +size 95016407 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd31623486b7939f6dc7a7d2d81f52c7b60d9397 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a09ddbf8e0cd8f1d2bd1261f5b13de012c99588878cb945cb2e87d5549eb5a5 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1057dc3aeff15371261279ffec05653cf999330 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e302b2b913e241373da4d9d8dcb332e104aca5a0c14365ff0968f09e5caa33f9 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c923f2ea0fe5a0686395b2db89eceab8fbb156cd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06f15d784d4a402a4a0b97d3693eb32f9e14cfe16d27de47d309c090e1d78803 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e3d369c40b67af6e7985407c9fd5ba16fdecf13 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef5ac2df017dc16deec83790a894e80be2490faa9941600ae7d97fc348684d6 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f1dfdc8c58be8ac86c48c8b87a30fe2d72d056a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ebc1fcef7c2f00c20016ea8c1d2c49370aadff9a559dad553de5113bf1821e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b0e9d1edd10c22a5383cbc676f6b29f7c259a29 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f66bfabe5b28d732de12ce01e947f8724ef71a3bca4ffd16cfb1c3afba40e20 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe5482bb72b5a8ff5154f79a2fcd2598d3c0fa5b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2f55f519202bf071def45b875a850818b491b9bc638773a65b52e8aad83812 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..688b85d6a24f8ec2c71093487ea2917fb69d62ab --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85063895aee61362dcec9d3440cadc407527ce68f8fa64bea5f668d0dd4c4e47 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fa8d6fe1e76c83475d7b7203618f16b4f122ae6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e7a00b2152187d5cdea98847eee2b151d6e704816000fe2657da38a744c527 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5bee34a31c3d98bced00db7569206aac0f86b4d4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafdcb98b4a4c6f970eacf78dbabef444357e805d8d537d1612089a1c14d259c +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6acc2fef1c54b40e2c1c0b0ba7ac231e3c47f77a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57f1bf9260e6c866261381fb3ef75cc9cda46b3ab029a11cb897e214d3032c8 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f3209db1c2d33b21d62f595eb62b36a39d3a172 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cccf99a17bdf7b9711aa9b8fcb1a82dda4066397f4788a964433f1482ec8fffd +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3f98443b78e3bffc2c6df767bee0924fcafa9f6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e07d0a1f353d93522d9803c6cda607af873e2c543ef600d97c91ef74e418c18 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80c6c533121516f4130eda58e910e93a2dcf9729 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4458e0362c8146f99c970df537007d6b3c92d21942b020095ba539b3e539c9b0 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a7de8ea3f33a928a278e2bb86302053e01d724b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c176eff690084139adc71bca0869865c0fbfc29cff74f34686cc9b226ab11ce8 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd71d82a19b153269fbfcce41d9dcade6e6a24bc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51764a456ea6a731ddd7653476255b9739c1dea4752c9eb4b451175ad92c7b67 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0bb7a9a1e0f112c859fe5ca584291048f8890c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8378b75dd64d1d22da28a6677efff6ad1e01b13249f8298c5d52e138aef574 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fcdece624c83d0faf5ce85c55197a2505fb48d17 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84dfd8cc031829977cf0e579f26c169139ec256536442cf110d5afc206deed6 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01704e316271452cfe16a542f3b2abbadce5d983 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820b088a5f7626b6b89f70ae34d68fcdb6c5e0de1ca3ec46ed409c2808cb7750 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6293c45d70a46d50567da41904940a2ecadd814a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8a8a0ff7bf544bac762f2e3ef46ff29eae35426e45a6bdff571869ccb913f5 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..827d47f0b14659c2fcee8c93f97d379c2f0d0389 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd51ba4b9ac0c9c7dd1cc057c487ce014e97986675a1717288aa456d43c91276 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..716fb537afbf46ee5c2f6f5d3818208341090c44 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:148397e0425f2fd0a1d40b0d9217b7446db1afaaf83cfbe613da79baf48247c6 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0e1cd0504619ed0a999f8513a5694a093256414 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71b91b18ceea6c52706e7d0446f8be108730e1d6074041102889908b663d4d7 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..de101037cc022053415219bd1143bb7478ff032d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701f3eb5f7d144a23b186ce509286db16d1ebf486d98b54e48357cff1c913a96 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e59cdbbea069d9989608ab7566b812422e598160 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba56b1cb28c66ca55226b936829e0afae1992da75fe01528c4150023fdc303a +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6dea6129eb18c96af4ae9e543b0c418a8b6f548c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a1cc4cf37ffe7c536d605cac0bf4e75d6d7cf2922b59e38917a8c25c0d2168 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17d0ff82e20b33bbc5d40781267db33786eba767 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80045a08c4bd47b01e1d8202db65b734ec0b84b93768f0e7c69925f9d6f6b39 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90c266d7b5d7c3e2626b9358cf2db3408b177fb3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205bd00722abba4a8716ae324c5bc5e58ab1763f1fd664886dc7ad1ecc8ba043 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..774d5cbc1b5ae9c4cc5cbb4eff676bf59cd25ddc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3bad66f2784ad983c688a1a600b5107631aca838f0a380c7b7ca3261b9593d +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..28fc22f2e9b6a07c4cd53eb11c01d47ec4179809 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:654a7626cac1b5c70df0f45320d934b286210fffbd3f80d02728f327ead8a31d +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2c26f483d1aee7078d1818106c0abf151cdb7ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a9821bbeeccc27cca329142532c28630bb7d0251596e970933c6d1cb81a5d8 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..740aa863d7e971277721dec2abbfc6a859059da2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8debbbccfd246086498c12061bcbe86fc7bfba12c607d980bbfe17adef8007b +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85ae8b30a7d3b7ae2c94e57ce7c121d719e26b8d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eee687adc166ff959731743626ce7f461e785510d011a4687b18d7a411bd0c8b +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f49ea2480dfb90dd42b0f13ade4f2adc117e3db --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7da3559e4bb7ffc04a6c3fa2d8d61755fb9c007da52b31cef38430871ee17fdc +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1f243b3493d3d1293870f7096c33092ff7f9938 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4f9c95691d52470f4e5dd40878e085d893489f80ed85b116c325c29d7fae88 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7678428516211736841ef00acbed825c6c2bdbc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1417f3100c63441d1c67c4564e0baf2e388afd90921e72a4881ec502deaf09b +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a82d53e94594081f6233d9b3b797aaf5550d209 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a25dffab93de46c101bbdd920665062351dca6812e419256cd400028fcaac8b +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e636c2137e262cf795d126a42639e9c482b9eb92 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690bd5c483208832388bc99873857580a71c77de4c71049c6e455c189a395140 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf5f4f46bb7290a9039e438df6e60f50eaf2f12a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babd4e3ad9955b6c6d91502cf84cde77bf2a8e102d45eac5fc13441f0c75f0f1 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8dc62dfb1b67232e306115885e6d53e8bc249dd --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9680acadb346494d125586fd4dd207ff4b4f171541675de273eada5345b33706 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a799a4ed329e71f375dea4cd280a1e6d7601d3b6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a429ea552f42f92bbd4b5775704ecf89bdeed3978f5863bd0e0310c1b0deb2 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31be18323d9e913e5a48176a75ee703f7c9e6444 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eee8da3410545e8697e7f8401a2ebaaa8dac0ceab34c182327062540caec5126 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a17a414186316930562c695f97f9086bb056afa8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65eec0020924f2de2dc3a39737120949857ef93b1be39aa0cefdef8d69da03f0 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cd2ebbdcb4607d760303c095c897f358b954d2b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7324d2acad37657bf34e4faeff50cdf319daa21498416a649cec9be3d927eb1d +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d4ba425b4f8212ebe87b38073d2010ddedeef71 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5872d1a9bb6634797b7e67242ab0486f96d800a7d6779dd1aedec363ba61c80c +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17e50b4ab662de13dc61125e900d000391d920ab --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9370106a9f9d7690bf37b5f3b2ed05cf3a80d9cf72133e672b454496781c0675 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20d601331a5806473f831404eb0f7695c2605c54 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08711c19307228bb6f9ab331ea1a1c0dcb68fe03b7fe0a9a47c12a0d459695a7 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19819b548e8e1eacd060bf03f991cb00fc9c55ee --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf9e2aeaad04bd21cb01140e1b2e869ff3a91b6a0b8e2a7059c1e99356bff7d +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50f1d025203e94bae10ad0ed54f23e28f2513889 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ed14f7b0b188a29f38e360e8bc6303632334179eb44b707c8aad247e9bf52e +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..61ccad7a4eb2999f7dacace13fafb7d9d0e6ed6d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2fae5f3d61e7fc9d2b6af182d56f17bd98331d89b5e18532d5b9591496390f +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78ef85b5d3ef0e15ef677702096993d6b23d5b24 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718d3ceb572bbf1cbd16ac17c3bdf7247d81e0d491429e072546ed79ce492c56 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e64ab894d6ab8145c097e3ca21fef54cc78ed73c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97d89855f28eb8fa8392e76a4ff3a987bdabb3557d99bbe032e1e5e16c3d7b8 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..64e8e58d03c0d91bae7dd097d82ef5cc0a5502ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5039a3e5489c1ddff8ccb1ffa07c60566105e49a914fd0f271b838ede99c970 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d94a79db125e0b818ff8608057e7426b9ec7f1c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e70774603f84278476b96959921e43e422e0e97b85c67516e4ebf983407423 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9798860b81cf994dc0ab14db5150fb2e651b4e0d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbff6eafcaaef9faf99dfc757062a74989d243b197be357316be1d2b61b5672d +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8da1c66c76c8373fb55e3a46ad0f901adcdad22f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7ded68869d5508c0a914816c7aa9a8204c8ae570c92fa94af76a1e888c1a7b +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e656d182e01c1b34cf1d2a9688684ca144358c3f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9531f00e8dde3f0215b916bac87f52784fe29b4933b2394ae6d35f17b2abdc +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5bb42950e1b4b50aee5f248a639ec64c33ef9440 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885000a02039a62f26427a70d3df1552d40f0915ba00d8cdeb3568ad0333ed21 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1f1b40df1ad24a7dfbdf9c7aae722dc65c7dace --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23484b542c3721b434223b12f8e380b79e13bd0222a0260c079b61d069b01e79 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5cf0bf92b24b80969f4f868ed3d49bd3534fe96 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a7fcc776b239a158f04a4b590c37a24e70b1a663edf6b99002cec1622e14f7 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7189d6455f8c6e5393e9d7b6141cc6aafb54329b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60762f88244156b5b869c159a0de12ad9c7c599cac64e7cf86c83ee9319823b8 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..113e2a3493a1ca9384ab6f161904ad223c73d6d5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d065b54b86049ca7e4c11033cfee335e00a990802c73f70ee0ca2cec15ef98 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a47a2765245bab10a08fb218f3962ec00edcdd8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb45b9e9b82005fdf64359e4ec88aef4411d4d8259229e9e49f6dbfe786cdd0 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f23a069b8757f4a96f681bdd00e0de4769a2d582 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafe29cdc0b8bc883fbe88850c2e946898eafe613c9a3f98885273475b88b353 +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a999be95b41e3881366b676489cd87b329e36d93 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043f8b8c111a543e7a36a80b0e60e0848c1baa2cc13f1f6ae8793096f57e0644 +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0c69329c8f2b490f2322e8deb36b494e0575bd6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d49902c64855f799b792d8761ffef951a4117aef4a620377e6929b02904691a1 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..06e1dbe08b0a57e5326d80368044321345adcfb6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c170665eba0d19a723066fcec508961f015ffe7d28b2ababce45fb0258a2c8 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..44ea48f11a4b67089f2ec7e2933f990f7dc8ff4d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b0effd4bd62d940d7a5bd1440c9c6e159ad233d2352af38198590dbbd71704 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d34da730252fb3486de83a65ff9333790e81563c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003bbd9b87ff0fb2c9bfd9bdc74e9cdf48001077adc57b850d2558c71c0c0bc9 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8775cc9fffdcd773871bfd988b3cc968d520d70a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12620a4ae53b8d3ab8413004608c6bef9bba5d3e8631493248b3d797296bbb5 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..926238c5064f984a0f3c1c67a556e504e07ecb93 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436bdd67571ee419185b3ae7c86a40f345aceac422ace1a563e9c97ab09db236 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..72e8a82a0c57fb934ab6f7ff5cbeb25f323efc18 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02298ab97ac511d1c24e951354a814b1c0d164e81a49544b03155039564245e9 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6861630a3265c9ab1270f967e6a147636e7831f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227d65da5319e234a7e99d94075ed65d28fa39e9c618fe4e1bdb64606cd72552 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29acb1c89078a5852665855ecf365ded6f4ada1e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7d42da0aa2cd77546bfe3c2adf87b8a85b52d58319f26b7fe9400b24c2970f +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dfe201cd6e27a2ba7c4b1fef17afe08ba8f9ddc --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c586b33b7786387b5e6aa96c1c2065333aa5caff2fec98b57b5ff305b0a8ec08 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0febaa8ca425a75da60596fb0141c452f4c402e --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613cd6c61f9dd8ed86eaf67b00686199bb7811aa2006b0dfb0140ce4bb6ee0a6 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..458e7e0ad9238cd854bc6822202223fbefc8e9a7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4182bcf9b6d5f1b3e6597b711745c5be968f2ec6b2448d7a7ad42c062ab7ead4 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67364dad1b52479251bde87653eb836e4e82e037 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84bba916ba699e1b68a8e5a338db0e84ca9d0fc2668584b4e6297990233d2858 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60b43dd573d821c98589552112b033a85c28647a --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde82440c22ed0788fbc5b23c1d2c72854f7e7ae3ff43a23b50fdcbefabae3ef +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..40f8c4a45f26b465eff3815a45599ac17b313b9c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af9f77c4df4e0fec79f92b8f8b8a22e08ae613d530c9a6e38cbd7b79d36c437 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aaa279103c59b73d5b06a2c343eac74db39e19d9 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ffd5176aef8723d174b4cd284497b64481a108477f13920432c1c4d20e4f01 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7548470a33159789288ff3945849e6967a6b0bbe --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d721cd2ad225d981a5f82af1e0ad2a6bb4fc9162463b71f4110ca3856c85e320 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26d6f32c155642bbbdc0b1874c394caf740ccfda --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662e68dacd4ea9f2572f3d547d6583040cd83c5dd03f2d1b93e15bb9540e2162 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..968b48c6cb349212ba00d94761c179bff67792f1 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7086a3627b3c698dda0e3520bca4d8733dc2814a8e851cb8110cdb5ca88219dc +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..324d8d60636a72f87c54f12cd5311495e7e65f32 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6086708e65381eacad432f32908d0ccab26c852f82e0cffa7b8638563d809f9c +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0117c3889e5c346dc4dc8ad222414bb9578ef7b2 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d8fa2fcf75b8a70786154ad55b5991283469033c06d7d916a54830fc3527c98 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c70dae42b9ea789f4029c8532433957146227a71 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ccdd9ce5825180cb1ba3c69d01a5af5d317ef2a83ee0349b24b3134e9b0fbb +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d4a9968f54a959b4a3e8c20de3f0f47450f6843 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a14fab0d4aaa3dba92b37b4c0ca044a2dc186d2a2ecd027345004cc38c557c0 +size 95016471 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1df667937cb39b22320128b0135c539d0300dee --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a838919a9a1934e6bbf23da4c49ecd8012f3f6b534f7957c7c1ef934fcdeaaa6 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e7ac204fee25260fdf5a18f4ee7a6b263261284 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2f3ff9d305a129e20e70fc2e6afbedb14ed582d0f7f5d425d901d4d1be62b7 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dce39f1ca99ca5164495e8076970e7493993cfb8 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4733e4de41c132dd66577dbc41edf7e4890e970ff78f045706481d02186e836c +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..abd339a4d3f942194aeb5ddeb36fa1a1f8ba3e7f --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5253324f297f733aa4b3ee43130765a2775ead58dc43de07196cf9a5edfc22a +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..812c5ca43fd48fed8f36d5c95b75ebeb6a3cd28d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ec92845fb011d3d7b28553bb1264efb4798821f785b93b7a2a47ddc959510f +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98bb46412633145844ceec3316910a79d944eb53 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6796022ab604d7bbe3b8c419486171cd3e7892adff1f46d47aef965079681803 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc629c4f1f97dd058d35e0c6d496f3573f23080d --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa128c19d9ff78a19b4a81e1f12c81b7bab848c614704832dc9a6d47f0b0ba52 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4447658b9c90a653ebe6398d24edc81fa9b636c7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f47223a47e320e50d47cf7b991a39a736893ae0b32b1a14757658bacde90b8c +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..618ba09691947f7cbbce9c8b7cd92f35f0957a09 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea83bf19d11c7beb54bc2119af154e733b2ae643b0d18eea8e564935b58cd3db +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..acdf8c658a497449b8e4a19d45f1bc66a2f461ae --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd013ba161751444edfecf80f36961a1e88285d0c06fb9d641548b5b5a18dfea +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4a93301809a1e041c39725ac7404c9f41b70871 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd2476209f808e56034f71cda49cde9b3fb1f8a7f04f7b50f76ca1a08dca3643 +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f10dd1e4adc0bef34d498941c7307a68d007542 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5f004aeff3918abf775ea80a891991630b38208b8793962bc774e01a2cd745 +size 95016418 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e7061abb247ed07ccedd95a633cdc384fa3a71c --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1b715340fb4eda08ec7e48bfe0eaa1183859048de83c38680e22ac0c008b2f +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3084353f2141eed936392dbc29ba331bb5980b81 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d4cacf031e2ea3fd214f74045ddec2a733d7564c3320c7f2591be36b338983 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e8ecdb3182a507a2de3aa0037cb4b713ac7c947 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f049ac3ac3ce0789b99ee227477cfd31bb18e2298d7789fb88539555537a3a8a +size 95016034 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a74d4dfa66dfffac27da4799c4a89eb2251c99b --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e246fe70bd652ad5cfaf15dd2f9f8b3b4d9ab1dbb86ae4b7b9ebc037a2bfa0 +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..977ed10d731926ddcbd09618621a53830db207f5 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5d80e6d05d1c5c59f736ffe7eb91e9e667793d6135aef9a645de90b1573ca0 +size 95016162 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c8ff06fc54f85b354f8e6f27341eeb0c2003fe7 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0fc0b872ceeac17569099c6471d008d6288253ad14dd38325a8824345f7bfc +size 95016546 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0ab30873cc128e6a79c93f988b9afc2ee6241ea --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff503c605f8beee4a56a4ab0441ec62d5a665e85ed5e1fd44ec28fb9e5aad742 +size 95016098 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..176b58314876aff54a79dd919482959dc0abc5f4 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4a244dca11faef7963e09b35d163e711e3876b5ba4e7d42407dcbdcd6d9cad +size 95016482 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..114608fa11e5599e502cd80b961a4e93514a45f3 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0414aed2a2cb539acabd6d4b96cab8ae76ecef932cdf8f279fe407d53143da1b +size 95016087 diff --git a/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2f74aa7683fbf2d5572f13581aa18a60ecc31c6 --- /dev/null +++ b/3b977b77b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7563e027fab1bef3943b65fb59c104102a42e3ab46b752b62a860567279cb91 +size 95016471 diff --git a/3b977b77b/global_step73814/layer_01-model_00-model_states.pt b/3b977b77b/global_step73814/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3558d5545807b92e16643bab57b5dd7f3f4ccb5 --- /dev/null +++ b/3b977b77b/global_step73814/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5657999a01a66b1e201733833591d8f305294daefde3d4a866f83adc576318c8 +size 308249859 diff --git a/3b977b77b/global_step73814/layer_03-model_00-model_states.pt b/3b977b77b/global_step73814/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ae5b5217128f4c30b82a01090a518974ff32fe2 --- /dev/null +++ b/3b977b77b/global_step73814/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22adfb16db3de0f3a15ee362b72ac6e207b26450e7bd9438a3204c31e5d66800 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_04-model_00-model_states.pt b/3b977b77b/global_step73814/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a6c8a874c3cfef88a4962d4f1600d73c82a4adf --- /dev/null +++ b/3b977b77b/global_step73814/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c91715f1b15c9e8508a4ef0760d6761de3f5675e01c6e429dce5a392ecda1b +size 208092163 diff --git a/3b977b77b/global_step73814/layer_05-model_00-model_states.pt b/3b977b77b/global_step73814/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4826f94daa04f7d93b5d34b4075b7dd8dc487be2 --- /dev/null +++ b/3b977b77b/global_step73814/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07215b775117fe288fbdc92703cb0bf0a829e830c82f757f47ce5c5cdf63a0ff +size 208092163 diff --git a/3b977b77b/global_step73814/layer_06-model_00-model_states.pt b/3b977b77b/global_step73814/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..efcb9be5764119dde839244abaebbfebdc94060b --- /dev/null +++ b/3b977b77b/global_step73814/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db79025fb34451c8cf17e500c469e7a2992c7a76813639f71e68297ed2048fe9 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_07-model_00-model_states.pt b/3b977b77b/global_step73814/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..37238011c77bc20b275af0bd66faccbc74dee65b --- /dev/null +++ b/3b977b77b/global_step73814/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8000ee2add422d286a310c8fe45597c758a868d2096558eec51d26a8665c058 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_08-model_00-model_states.pt b/3b977b77b/global_step73814/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a787f7f425e254737c3a37d32716781f11692d2 --- /dev/null +++ b/3b977b77b/global_step73814/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c75c3a287c5fc28cb628f3bbaaae480b915d0ef93a14e04719a28a4183e1089 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_09-model_00-model_states.pt b/3b977b77b/global_step73814/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9cec5377cd8e3d463f64b3d1266f2c244f78d6f3 --- /dev/null +++ b/3b977b77b/global_step73814/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808b7acb095c27c1d2da2d5d4f40b2b25b07de79ac29e43a4a0f1c1c097a3590 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_10-model_00-model_states.pt b/3b977b77b/global_step73814/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b003a86edd2e1435f80166c8ddc6f1db7de6b24 --- /dev/null +++ b/3b977b77b/global_step73814/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fabed0c9ae927321b7bbcc72f2f200746d73c571b2c08faaf5315f6c404ccd65 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_11-model_00-model_states.pt b/3b977b77b/global_step73814/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e41bdcd208a1370a675fc2af20f1ebb15822f6a7 --- /dev/null +++ b/3b977b77b/global_step73814/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35581983e0ead15cf1b294ac8510d0311b3fa45a95d0bae04eb624b1deec5a4 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_12-model_00-model_states.pt b/3b977b77b/global_step73814/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2aa3d15112724a5a02dbd0c2f8071d4ca39d895f --- /dev/null +++ b/3b977b77b/global_step73814/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b2c8938c49e4b42f699bdfd32205522e919c3c01696937245592c0ebb5d98c +size 208092163 diff --git a/3b977b77b/global_step73814/layer_13-model_00-model_states.pt b/3b977b77b/global_step73814/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..739b8ed56623fdf6a5089d94c7d4cfe664ff5928 --- /dev/null +++ b/3b977b77b/global_step73814/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c3c3e5e81242fbccd8f5d76231e2705f2a74056a14a6e5c6f4bc166c84fe64 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_14-model_00-model_states.pt b/3b977b77b/global_step73814/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9ec8a4fe3386bba67467dd5629e3f82f02993e8 --- /dev/null +++ b/3b977b77b/global_step73814/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61ab353351baeebe188559e1d8d99d8aecccc2b5907125165feaef8c25a9977 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_15-model_00-model_states.pt b/3b977b77b/global_step73814/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53cfd236923b9bf41846498c2e3990a74e0d44b6 --- /dev/null +++ b/3b977b77b/global_step73814/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b524ef3aae33910165cd14ff6283628211462999f748804ba9594269e50b6a1 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_16-model_00-model_states.pt b/3b977b77b/global_step73814/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3067e45124406e1bf15e520a08eb0933fe3472b --- /dev/null +++ b/3b977b77b/global_step73814/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e1aa4750db2854bd8b51416a454e7bc9ff7af3e5809e50c91e460093a979a9 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_17-model_00-model_states.pt b/3b977b77b/global_step73814/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5904e851a8ba3a08b6365556f6842af87789cfa9 --- /dev/null +++ b/3b977b77b/global_step73814/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469c665a23b40339d6aee8420b8751f7f3b38462ad54a938cc93b651b53e1c6e +size 208092163 diff --git a/3b977b77b/global_step73814/layer_18-model_00-model_states.pt b/3b977b77b/global_step73814/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3fd3a78d0f76c4df5fc8dee684da4677437660e --- /dev/null +++ b/3b977b77b/global_step73814/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:209c17d1c1484d9eafcba4f0aeb9cf183e511e731c31173233f32239e8f20603 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_19-model_00-model_states.pt b/3b977b77b/global_step73814/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a22986e528d9973bd9166ddce60393075a4bdefc --- /dev/null +++ b/3b977b77b/global_step73814/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a80e87d4693711e2f97f74ef13da76e5747ea8bd2f66001d4f068599daa51cd +size 208092163 diff --git a/3b977b77b/global_step73814/layer_20-model_00-model_states.pt b/3b977b77b/global_step73814/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f0cbd829baf48a109f9164ff508b7e5760f9d3f2 --- /dev/null +++ b/3b977b77b/global_step73814/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb29b9623d78c2faabeacde1bb625339101b485dd1be4c7f6e4785c9a288a8b5 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_21-model_00-model_states.pt b/3b977b77b/global_step73814/layer_21-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9dfd57ad08b7ce7b9d1ad8410201a851271543e9 --- /dev/null +++ b/3b977b77b/global_step73814/layer_21-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723b2aa8444a76ddf3ae087e0f7c23fe665d95aa4cd34de8f6cbfb7661c2a60f +size 208092163 diff --git a/3b977b77b/global_step73814/layer_22-model_00-model_states.pt b/3b977b77b/global_step73814/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac226507e80be720ccfca1be87df06bddf34170b --- /dev/null +++ b/3b977b77b/global_step73814/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a4e07b2a6f2966ba8d28933653bbcd9081808614421aa0025601f6dd416beb +size 208092163 diff --git a/3b977b77b/global_step73814/layer_23-model_00-model_states.pt b/3b977b77b/global_step73814/layer_23-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ecb2182b38b2aeaa9a2ef0e3f304a5fb063d8f9 --- /dev/null +++ b/3b977b77b/global_step73814/layer_23-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa0f968a565ef4a39ee974384508bf97db08c5c0b63fd367c7a2926b921cf55 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_24-model_00-model_states.pt b/3b977b77b/global_step73814/layer_24-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3af4d72cc11e9cb479c52edae33a9af0165145e6 --- /dev/null +++ b/3b977b77b/global_step73814/layer_24-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f643348b434695b3ff6c1b2606b066e01a71ce1f270bbb1b7b0c5f5c87f5ed6f +size 208092163 diff --git a/3b977b77b/global_step73814/layer_25-model_00-model_states.pt b/3b977b77b/global_step73814/layer_25-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01580066ee36b506000e39f50d845a9fa9c0b389 --- /dev/null +++ b/3b977b77b/global_step73814/layer_25-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a1a4369bc61e3e200139fb74aabcf2ddbdb48af57337d25e1422408921efb8 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_26-model_00-model_states.pt b/3b977b77b/global_step73814/layer_26-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef120f4a37ba34ef4540144183b76aa0e9f12524 --- /dev/null +++ b/3b977b77b/global_step73814/layer_26-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c435b54f6c38a05d2a75754ed7f14627b3b36c3ea98656bfcbda65cda57cde +size 208092163 diff --git a/3b977b77b/global_step73814/layer_27-model_00-model_states.pt b/3b977b77b/global_step73814/layer_27-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..392cd0d39fc1abf786a700ec422cba6daf1f53d1 --- /dev/null +++ b/3b977b77b/global_step73814/layer_27-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45dce855bf26a661ad56ca874eb80aad1a40601bfd4dad67527c0b7e1f0a8833 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_28-model_00-model_states.pt b/3b977b77b/global_step73814/layer_28-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..408dfd9027ce943aef322e482b6c8053c4e7b62e --- /dev/null +++ b/3b977b77b/global_step73814/layer_28-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108177db541a2e66175035621bf6150f71dbdd84b79378792ef61d5f41f6b5c8 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_29-model_00-model_states.pt b/3b977b77b/global_step73814/layer_29-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c895a04a5deb4cb5e60d340c023f18077781f8b7 --- /dev/null +++ b/3b977b77b/global_step73814/layer_29-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26df9f45f002bc20d5842e85e5704dc2686a85c56f8374677d3952b5b8464d33 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_30-model_00-model_states.pt b/3b977b77b/global_step73814/layer_30-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aae80bd5c5855c082ebe618ef7401a9e5ceb0eaf --- /dev/null +++ b/3b977b77b/global_step73814/layer_30-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c025f5f33b8408185db37747aae1dafca5d632e28a00f7565af6c36ba54cb1 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_31-model_00-model_states.pt b/3b977b77b/global_step73814/layer_31-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31c7b4a62ebd4ee17ec9d7a553493fe83b737c5b --- /dev/null +++ b/3b977b77b/global_step73814/layer_31-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09af13f270eecf975ce793469e39ba6cf2f763ab1939a63d9850772c90d285e3 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_32-model_00-model_states.pt b/3b977b77b/global_step73814/layer_32-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5cf1f206bd15bc35baeda67c8ee50779731114d7 --- /dev/null +++ b/3b977b77b/global_step73814/layer_32-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6dca637dc8ebafa04de19a7ca76da65e453e110c7d3be379953f50995397a5 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_33-model_00-model_states.pt b/3b977b77b/global_step73814/layer_33-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..558dfd4c00a324ff66ff0c8a56f028f853f3935c --- /dev/null +++ b/3b977b77b/global_step73814/layer_33-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aacd9d87c66ca2fbf77bfcbb293f99e4cbd11b9166ab6870954ff6b68c008411 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_34-model_00-model_states.pt b/3b977b77b/global_step73814/layer_34-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..be18ba74073c36e5d61e2e8b0678935d05e02965 --- /dev/null +++ b/3b977b77b/global_step73814/layer_34-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53396a0fa1e5739f939b4170c5422bb98aa836dfececcda15d1f6b112368472 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_35-model_00-model_states.pt b/3b977b77b/global_step73814/layer_35-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..04c1f83c18f1a72b1b1adf9e3ddeede6e14539dd --- /dev/null +++ b/3b977b77b/global_step73814/layer_35-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f488c73794c01d11fc6561ecd1743ac6d2ac68ac653b2727bacbe191de19d53 +size 208092163 diff --git a/3b977b77b/global_step73814/layer_36-model_00-model_states.pt b/3b977b77b/global_step73814/layer_36-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4f85537a26b9b69745634fa847d9c59908ff02a --- /dev/null +++ b/3b977b77b/global_step73814/layer_36-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ebdc5834543dcf38025290145e95a7849fea54ff09e9ec81b7ed17b643aa9c +size 208092163 diff --git a/3b977b77b/global_step73814/layer_37-model_00-model_states.pt b/3b977b77b/global_step73814/layer_37-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fa9cf1c5ae4d157a78634e2ebb7b9836a791c87 --- /dev/null +++ b/3b977b77b/global_step73814/layer_37-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9088210b230e7e18fe5c9522ab1eb66890c0eb8e60b66d03eee86713365ed01c +size 208092163 diff --git a/3b977b77b/global_step73814/layer_38-model_00-model_states.pt b/3b977b77b/global_step73814/layer_38-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ced7decc397f560993ce40aade8e1f587bb833e3 --- /dev/null +++ b/3b977b77b/global_step73814/layer_38-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb21e6e3d1e5901490b23cbe6301544287c8daba1541ca338578102b97b8aff +size 208092163 diff --git a/3b977b77b/global_step73814/layer_40-model_00-model_states.pt b/3b977b77b/global_step73814/layer_40-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8f76b43214440f39bebbb5735f639c6f846aefd --- /dev/null +++ b/3b977b77b/global_step73814/layer_40-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c77fde7f20d30f1088ffa583d4e96d754ceea2b2f3bb28dbdf81471c0332bcd +size 12995 diff --git a/3b977b77b/global_step73814/mp_rank_00_model_states.pt b/3b977b77b/global_step73814/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87aad67881bfbc3e81ec6ebc13e8ebe1fdb3321f --- /dev/null +++ b/3b977b77b/global_step73814/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05fdadc25a883eb65e7362a3769d25563317e9c1957e12ff76e1340b09d2198f +size 37363 diff --git a/3b977b77b/global_step73814/mp_rank_01_model_states.pt b/3b977b77b/global_step73814/mp_rank_01_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9403325880eabd6a06fc0f6c746af0de0b24e863 --- /dev/null +++ b/3b977b77b/global_step73814/mp_rank_01_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c12165c36437aa1051df6e1855ba246fc7f116a318f3af8433b04ebe9c94757 +size 37491 diff --git a/3b977b77b/launch.sh b/3b977b77b/launch.sh new file mode 100755 index 0000000000000000000000000000000000000000..6c3445845a5dae614feb4b8a1206322cd7bd9050 --- /dev/null +++ b/3b977b77b/launch.sh @@ -0,0 +1,53 @@ +#!/bin/bash + +# Launch script using torch.distributed.run(). Used by slurm +# scripts, don't invoke directly. + +# Samuel's fix for apparent error in SLURM initialization +if [ $SLURM_LOCALID -eq 0 ]; then + rm -rf /dev/shm/* + rocm-smi || true +else + sleep 2 +fi + +export NCCL_SOCKET_IFNAME=hsn0,hsn1,hsn2,hsn3 +export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK +export FI_CXI_DEFAULT_CQ_SIZE=131072 + +# debugging (noisy) +#export NCCL_DEBUG=INFO +#export RCCL_KERNEL_COLL_TRACE_ENABLE=1 +#export NCCL_DEBUG_SUBSYS=INIT,COLL + +module --quiet purge +module load cray-python + +module load CrayEnv +module load PrgEnv-cray/8.3.3 +module load craype-accel-amd-gfx90a +module load cray-python + +module use /pfs/lustrep2/projappl/project_462000125/samantao-public/mymodules +module load suse-repo-deps/sam-default +module load rocm/sam-5.2.3.lua +module load rccl/sam-develop.lua +module load aws-ofi-rccl/sam-default.lua + +source venv/bin/activate + +MASTER_NODE=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1) +MASTER_PORT=9999 + +echo "Launching on $SLURMD_NODENAME ($SLURM_PROCID/$SLURM_JOB_NUM_NODES)," \ + "master $MASTER_NODE port $MASTER_PORT," \ + "GPUs $SLURM_GPUS_ON_NODE," \ + "CUDA: $(python -c 'import torch; print(torch.cuda.is_available())')" + +python -u -m torch.distributed.run \ + --nnodes $SLURM_JOB_NUM_NODES \ + --nproc_per_node $SLURM_GPUS_ON_NODE \ + --node_rank=$SLURM_PROCID \ + --master_addr $MASTER_NODE \ + --master_port $MASTER_PORT \ + "$@" diff --git a/3b977b77b/logs/2100040.err b/3b977b77b/logs/2100040.err new file mode 100644 index 0000000000000000000000000000000000000000..ef33909cb01ded8e88b572857b4247f24f4883a8 --- /dev/null +++ b/3b977b77b/logs/2100040.err @@ -0,0 +1,4290 @@ + 0: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 0: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +58: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +58: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +53: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +53: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +52: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +52: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +48: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +48: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +56: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +56: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 2: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 2: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +54: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +54: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +62: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +62: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +60: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +60: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +24: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +24: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 1: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 1: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +57: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +57: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +51: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +51: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +55: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +55: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +61: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +61: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +25: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +25: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +26: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +26: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +10: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +10: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +46: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +46: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 6: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 6: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +20: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +20: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +40: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +40: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +38: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card0': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card1': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card2': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card3': Operation not permitted +63: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +63: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +59: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +59: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +21: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +21: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 7: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 7: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 9: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 9: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +39: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card0': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card1': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card2': Operation not permitted +19: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +19: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +23: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +23: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +45: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +45: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 4: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 4: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +44: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +44: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +42: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +42: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +18: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +18: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +22: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +22: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +30: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +30: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +28: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +28: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +32: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +32: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +16: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +16: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +14: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +14: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card4': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card5': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card6': Operation not permitted +38: rm: cannot remove '/dev/shm/rocm_smi_card7': Operation not permitted +38: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card3': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card4': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card5': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card6': Operation not permitted + 5: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 5: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +11: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +11: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +47: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +47: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +43: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +43: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +41: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +41: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +17: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +17: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 3: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 3: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +29: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card0': Operation not permitted +31: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +31: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +39: rm: cannot remove '/dev/shm/rocm_smi_card7': Operation not permitted +39: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +34: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +34: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +36: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +36: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card1': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card2': Operation not permitted +49: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +49: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +37: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +37: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +27: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card0': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card1': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card2': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card3': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card3': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card4': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card5': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card6': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card4': Operation not permitted +27: rm: cannot remove '/dev/shm/rocm_smi_card7': Operation not permitted +27: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card5': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card6': Operation not permitted +29: rm: cannot remove '/dev/shm/rocm_smi_card7': Operation not permitted +29: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +15: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +15: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +12: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +12: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +50: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +50: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +35: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +35: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +13: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +13: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +33: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +33: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 8: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted + 8: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module scaled_upper_triang_masked_softmax_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module scaled_upper_triang_masked_softmax_cuda... + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module scaled_masked_softmax_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module scaled_masked_softmax_cuda... + 0: Successfully preprocessed all matching files. + 0: Detected CUDA files, patching ldflags + 0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... + 0: Building extension module fused_mix_prec_layer_norm_cuda... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module fused_mix_prec_layer_norm_cuda... + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. +28: Successfully preprocessed all matching files. +28: Successfully preprocessed all matching files. +17: Successfully preprocessed all matching files. +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 0: warnings.warn( +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +32: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +15: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +15: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +47: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +28: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +28: warnings.warn( +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +60: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( + 1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 1: warnings.warn( +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +33: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( + 4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 4: warnings.warn( +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +36: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +30: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +30: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +49: warnings.warn( +17: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +17: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +62: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +23: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +23: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +55: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( + 7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 7: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +39: warnings.warn( +20: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +20: warnings.warn( +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +52: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +25: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +25: warnings.warn( +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +57: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +10: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +10: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +42: warnings.warn( +11: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +11: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +43: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +19: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +19: warnings.warn( +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +51: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +59: warnings.warn( +27: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +27: warnings.warn( +24: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +24: warnings.warn( +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +56: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( + 2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 2: warnings.warn( +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +34: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +22: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +22: warnings.warn( +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +54: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +31: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +31: warnings.warn( +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +63: warnings.warn( + 5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 5: warnings.warn( +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +37: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +18: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +18: warnings.warn( +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +50: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( + 9: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 9: warnings.warn( +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +41: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +29: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +29: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +61: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 6: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +26: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +26: warnings.warn( +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +58: warnings.warn( +16: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +16: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( + 3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 3: warnings.warn( +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +48: warnings.warn( +21: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +21: warnings.warn( +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +35: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +53: warnings.warn( +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +38: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +14: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +14: warnings.warn( +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +46: warnings.warn( +13: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +13: warnings.warn( +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +45: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +12: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +12: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +44: warnings.warn( + 8: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead + 8: warnings.warn( +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +40: warnings.warn( +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +13: Building extension module utils... +13: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: +33: +33: +33: +33: +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: +36: +36: +36: +36: +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: +35: +35: +35: +35: +35: +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: +37: +37: +37: +37: +37: +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: +38: +38: +38: +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: +40: +40: +40: +40: +40: +40: +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: +41: +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: +42: +42: +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: +42: +42: +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: +46: +46: +46: +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +45: +45: +45: +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: +47: +47: +47: +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: +49: +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: +49: +49: +49: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: +50: +50: +50: +50: +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: +51: +51: +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: +51: +51: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: +54: +54: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: +55: +55: +55: +55: +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: +56: +56: +56: +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: +60: +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: +57: +57: +57: +57: +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: +59: +59: +59: +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +13: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +51: Loading extension module utils... +50: Loading extension module utils... +51: Loading extension module utils... +50: Loading extension module utils... +51: Loading extension module utils... +50: Loading extension module utils... +51: Loading extension module utils... +50: Loading extension module utils... +50: Loading extension module utils... +50: Loading extension module utils... +50: Loading extension module utils... +50: Loading extension module utils... +58: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Loading extension module utils... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: + 2: + 2: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: + 1: + 1: + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: + 3: + 3: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: + 6: + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: + 4: + 4: + 4: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: + 5: + 5: + 5: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: + 9: + 9: + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: + 9: +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: +11: +11: +11: +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: +10: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: +12: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: +14: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +15: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +18: +18: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +18: +18: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: +21: +21: +21: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +22: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: +23: +23: +23: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +24: +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: +25: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: +26: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: +26: +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +29: +29: +29: +29: +29: +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: +30: +30: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: +31: +31: + 0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... + 0: Building extension module utils... + 0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) + 0: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 4: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... + 8: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... + 8: Loading extension module utils... +13: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... +11: Loading extension module utils... + 6: Loading extension module utils... + 7: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +16: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +16: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +16: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +16: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +16: Loading extension module utils... +10: Loading extension module utils... +19: Loading extension module utils... +16: Loading extension module utils... +10: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +10: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +14: Loading extension module utils... +17: Loading extension module utils... +19: Loading extension module utils... +14: Loading extension module utils... +17: Loading extension module utils... +19: Loading extension module utils... +14: Loading extension module utils... +17: Loading extension module utils... +19: Loading extension module utils... +17: Loading extension module utils... +14: Loading extension module utils... +19: Loading extension module utils... +17: Loading extension module utils... +14: Loading extension module utils... +19: Loading extension module utils... +14: Loading extension module utils... +17: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +15: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +27: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +27: Loading extension module utils... +21: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +24: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +24: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +24: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... +28: Loading extension module utils... +22: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +31: Loading extension module utils... +34: Loading extension module utils... +39: Loading extension module utils... +43: Loading extension module utils... +44: Loading extension module utils... +32: Loading extension module utils... +48: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +32: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +34: Loading extension module utils... +52: Loading extension module utils... +53: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +33: Loading extension module utils... +39: Loading extension module utils... +33: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +39: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +35: Loading extension module utils... +36: Loading extension module utils... +36: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... + 0: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +35: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +58: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +37: Loading extension module utils... +43: Loading extension module utils... +37: Loading extension module utils... +44: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +60: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +38: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +44: Loading extension module utils... +38: Loading extension module utils... +44: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +38: Loading extension module utils... +61: Loading extension module utils... +41: Loading extension module utils... +41: Loading extension module utils... +41: Loading extension module utils... +40: Loading extension module utils... +41: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +63: Loading extension module utils... +62: Loading extension module utils... +41: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +41: Loading extension module utils... +41: Loading extension module utils... +40: Loading extension module utils... +41: Loading extension module utils... +40: Loading extension module utils... +40: Loading extension module utils... +42: Loading extension module utils... +48: Loading extension module utils... +42: Loading extension module utils... +48: Loading extension module utils... +42: Loading extension module utils... +42: Loading extension module utils... +48: Loading extension module utils... +48: Loading extension module utils... +42: Loading extension module utils... +48: Loading extension module utils... +42: Loading extension module utils... +48: Loading extension module utils... +42: Loading extension module utils... +48: Loading extension module utils... +42: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +46: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +32: Loading extension module utils... +46: Loading extension module utils... +45: Loading extension module utils... +45: Loading extension module utils... +47: Loading extension module utils... +52: Loading extension module utils... +47: Loading extension module utils... +52: Loading extension module utils... +52: Loading extension module utils... +47: Loading extension module utils... +52: Loading extension module utils... +47: Loading extension module utils... +52: Loading extension module utils... +52: Loading extension module utils... +47: Loading extension module utils... +52: Loading extension module utils... +47: Loading extension module utils... +47: Loading extension module utils... +53: Loading extension module utils... +47: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +53: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +49: Loading extension module utils... +58: Loading extension module utils... + 0: Loading extension module utils... +58: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... +60: Loading extension module utils... +60: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +55: Loading extension module utils... +55: Loading extension module utils... +60: Loading extension module utils... +54: Loading extension module utils... +60: Loading extension module utils... +54: Loading extension module utils... +60: Loading extension module utils... +55: Loading extension module utils... +54: Loading extension module utils... +60: Loading extension module utils... +55: Loading extension module utils... +60: Loading extension module utils... +54: Loading extension module utils... +55: Loading extension module utils... +54: Loading extension module utils... +54: Loading extension module utils... +55: Loading extension module utils... +61: Loading extension module utils... +55: Loading extension module utils... +61: Loading extension module utils... +55: Loading extension module utils... +61: Loading extension module utils... +56: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +56: Loading extension module utils... +61: Loading extension module utils... +61: Loading extension module utils... +56: Loading extension module utils... +62: Loading extension module utils... +56: Loading extension module utils... +62: Loading extension module utils... +56: Loading extension module utils... +62: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +56: Loading extension module utils... +63: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +57: Loading extension module utils... +63: Loading extension module utils... +62: Loading extension module utils... +62: Loading extension module utils... +63: Loading extension module utils... +57: Loading extension module utils... +63: Loading extension module utils... +57: Loading extension module utils... +63: Loading extension module utils... +57: Loading extension module utils... +63: Loading extension module utils... +57: Loading extension module utils... +63: Loading extension module utils... +57: Loading extension module utils... +57: Loading extension module utils... +57: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... +59: Loading extension module utils... + 7: Loading extension module utils... + 6: Loading extension module utils... + 7: Loading extension module utils... + 2: Loading extension module utils... + 7: Loading extension module utils... + 1: Loading extension module utils... + 2: Loading extension module utils... + 6: Loading extension module utils... + 7: Loading extension module utils... + 1: Loading extension module utils... + 2: Loading extension module utils... + 6: Loading extension module utils... + 7: Loading extension module utils... + 2: Loading extension module utils... + 6: Loading extension module utils... + 7: Loading extension module utils... + 2: Loading extension module utils... + 3: Loading extension module utils... + 1: Loading extension module utils... + 7: Loading extension module utils... + 2: Loading extension module utils... + 1: Loading extension module utils... + 3: Loading extension module utils... + 6: Loading extension module utils... + 2: Loading extension module utils... + 1: Loading extension module utils... + 6: Loading extension module utils... + 2: Loading extension module utils... + 6: Loading extension module utils... + 1: Loading extension module utils... + 3: Loading extension module utils... + 1: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 1: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +41: +41: Loading extension module utils... +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +41: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +41: +41: Loading extension module utils... +41: No modifications detected for re-loaded extension module utils, skipping build step... +41: Loading extension module utils... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 8: + 8: + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: +34: +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: +31: +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: +33: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +13: + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +13: Loading extension module utils...Loading extension module utils... +13: +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +31: +31: Loading extension module utils...Loading extension module utils... +31: +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +31: +31: Loading extension module utils...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +31: +31: +13: No modifications detected for re-loaded extension module utils, skipping build step... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +13: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 8: + 8: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... + 9: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +33: + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +33: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... +33: No modifications detected for re-loaded extension module utils, skipping build step... +33: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +43: +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils... +43: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +43: +43: +43: Loading extension module utils...Loading extension module utils...Loading extension module utils... +43: +43: +43: No modifications detected for re-loaded extension module utils, skipping build step... +43: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +43: +43: Loading extension module utils... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: +50: +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: +50: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +50: +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +50: +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +50: No modifications detected for re-loaded extension module utils, skipping build step... +50: Loading extension module utils... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: +32: +32: +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +32: No modifications detected for re-loaded extension module utils, skipping build step... +32: Loading extension module utils... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +32: No modifications detected for re-loaded extension module utils, skipping build step... +32: Loading extension module utils... +32: No modifications detected for re-loaded extension module utils, skipping build step... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: +32: Loading extension module utils... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: +32: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +32: +32: +32: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +32: +32: Loading extension module utils...Loading extension module utils... +32: Loading extension module utils... +32: +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +32: No modifications detected for re-loaded extension module utils, skipping build step... +32: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +58: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +58: +58: Loading extension module utils... +58: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +58: +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +58: Loading extension module utils... +58: No modifications detected for re-loaded extension module utils, skipping build step... +58: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +26: +26: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +60: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +60: +60: Loading extension module utils...Loading extension module utils... +60: +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +60: +60: Loading extension module utils... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +60: No modifications detected for re-loaded extension module utils, skipping build step... +60: Loading extension module utils... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: +53: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +53: +53: +53: Loading extension module utils...Loading extension module utils... +53: +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... +53: No modifications detected for re-loaded extension module utils, skipping build step... +53: Loading extension module utils... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: + 7: + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 7: + 7: + 7: Loading extension module utils...Loading extension module utils... + 7: Loading extension module utils... + 7: + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 7: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: + 7: Loading extension module utils...Loading extension module utils... + 7: + 7: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +34: +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +34: No modifications detected for re-loaded extension module utils, skipping build step... +34: Loading extension module utils... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: +19: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +19: +19: Loading extension module utils... +19: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +19: +19: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +19: +19: +19: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +19: +19: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +38: +38: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +39: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +39: +39: +11: No modifications detected for re-loaded extension module utils, skipping build step... +38: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +38: +38: Loading extension module utils...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +38: +38: +11: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +38: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: Loading extension module utils... +38: No modifications detected for re-loaded extension module utils, skipping build step... +38: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +39: +39: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +39: +39: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step... +39: Loading extension module utils... +39: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +39: +39: Loading extension module utils...Loading extension module utils... +39: + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 0: + 0: + 0: Loading extension module utils... + 0: Loading extension module utils...Loading extension module utils... + 0: + 0: No modifications detected for re-loaded extension module utils, skipping build step... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Loading extension module utils... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... +54: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +54: Loading extension module utils... +54: No modifications detected for re-loaded extension module utils, skipping build step... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: +63: +54: Loading extension module utils... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +63: +63: Loading extension module utils...Loading extension module utils... +63: +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: +47: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +47: +63: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +63: +63: Loading extension module utils...Loading extension module utils... +63: +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +63: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +63: No modifications detected for re-loaded extension module utils, skipping build step... +63: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +45: +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +36: +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +45: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +36: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +36: +36: +36: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +36: +36: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +47: No modifications detected for re-loaded extension module utils, skipping build step... +47: Loading extension module utils... +36: No modifications detected for re-loaded extension module utils, skipping build step... +36: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +17: +17: Loading extension module utils...Loading extension module utils... +17: +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +17: +17: Loading extension module utils... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +48: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +48: +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +48: +48: Loading extension module utils...Loading extension module utils... +48: +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +48: +48: +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +48: Loading extension module utils...Loading extension module utils...Loading extension module utils... +48: No modifications detected for re-loaded extension module utils, skipping build step... +48: +48: +48: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils... +45: No modifications detected for re-loaded extension module utils, skipping build step... +45: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +45: +45: Loading extension module utils... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +57: +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +57: +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +57: No modifications detected for re-loaded extension module utils, skipping build step... +57: Loading extension module utils... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +49: No modifications detected for re-loaded extension module utils, skipping build step... +49: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: Loading extension module utils...Loading extension module utils... + 3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: Loading extension module utils... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +55: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +55: +55: Loading extension module utils...Loading extension module utils... +55: +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 1: + 1: Loading extension module utils...Loading extension module utils... + 1: +55: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +55: + 1: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils...Loading extension module utils... +55: + 1: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +55: No modifications detected for re-loaded extension module utils, skipping build step... +55: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: +59: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +59: +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +59: +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +59: No modifications detected for re-loaded extension module utils, skipping build step... +59: Loading extension module utils... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +35: +35: +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +35: No modifications detected for re-loaded extension module utils, skipping build step... +35: Loading extension module utils... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +56: +56: Loading extension module utils... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +56: +56: Loading extension module utils... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils... +56: No modifications detected for re-loaded extension module utils, skipping build step... +56: Loading extension module utils... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: +51: +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: +51: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: Loading extension module utils... +51: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +51: +51: Loading extension module utils...Loading extension module utils... +51: +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +51: +51: Loading extension module utils... +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +51: +51: Loading extension module utils... +51: No modifications detected for re-loaded extension module utils, skipping build step... +51: Loading extension module utils... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +37: +37: +37: +37: +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +37: +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +37: +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +37: +37: Loading extension module utils... +37: No modifications detected for re-loaded extension module utils, skipping build step... +37: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 6: + 6: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +14: +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +14: +14: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 4: + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 4: + 4: Loading extension module utils...Loading extension module utils... + 4: + 4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 4: + 4: Loading extension module utils...Loading extension module utils... + 4: + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +61: +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +61: +61: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +61: +61: Loading extension module utils...Loading extension module utils... +61: +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... +61: No modifications detected for re-loaded extension module utils, skipping build step... +61: Loading extension module utils... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 5: + 5: + 5: + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 5: + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +15: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +25: +25: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: +42: +42: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +42: +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +42: +42: Loading extension module utils... +42: No modifications detected for re-loaded extension module utils, skipping build step... +42: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +23: +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +12: +12: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: +22: +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +22: +22: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +52: +52: +52: Loading extension module utils...Loading extension module utils... +52: +52: No modifications detected for re-loaded extension module utils, skipping build step... +52: Loading extension module utils... +52: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +52: +52: Loading extension module utils... +52: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +21: +21: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +21: +21: +21: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +21: +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +44: +44: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +44: +44: +44: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +44: +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +44: No modifications detected for re-loaded extension module utils, skipping build step... +44: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: +28: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +28: +28: Loading extension module utils...Loading extension module utils... +28: +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +28: +28: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +16: +16: Loading extension module utils...Loading extension module utils... +16: +16: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +16: +16: Loading extension module utils... +16: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +62: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +40: +40: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: +46: +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +40: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +40: +40: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +62: No modifications detected for re-loaded extension module utils, skipping build step... +62: Loading extension module utils... +46: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +46: +40: Loading extension module utils... +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +62: +62: Loading extension module utils...Loading extension module utils... +62: +10: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +10: +10: Loading extension module utils...Loading extension module utils... +10: +40: No modifications detected for re-loaded extension module utils, skipping build step... +40: Loading extension module utils... +62: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +62: +62: Loading extension module utils... +62: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +18: +62: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +62: +62: Loading extension module utils...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +62: +62: +62: Loading extension module utils... +18: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +18: +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +10: +10: Loading extension module utils... +18: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +46: +46: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +46: +46: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... +46: No modifications detected for re-loaded extension module utils, skipping build step... +46: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings + 0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +58: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +58: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +55: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +55: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +35: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +35: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +57: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +57: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +32: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +32: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +43: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +43: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +51: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +51: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +36: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +36: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +49: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +49: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +52: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +52: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +63: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +63: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +45: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +45: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +38: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +38: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +54: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +54: if inputs.grad is not None: +34: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +34: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +48: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +48: if inputs.grad is not None: +33: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +33: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +40: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +40: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +50: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +50: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +60: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +60: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +37: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +37: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +42: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +42: if inputs.grad is not None: +59: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +59: if inputs.grad is not None: +39: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +39: if inputs.grad is not None: +44: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +44: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +61: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +61: if inputs.grad is not None: +47: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +47: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +53: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +53: if inputs.grad is not None: +62: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +62: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +46: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +46: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +56: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +56: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: +41: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py:1200: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at aten/src/ATen/core/TensorBody.h:485.) +41: if inputs.grad is not None: diff --git a/3b977b77b/logs/2100040.out b/3b977b77b/logs/2100040.out new file mode 100644 index 0000000000000000000000000000000000000000..14d37781c7aafeaac2d0edd691e0b067f9ff1c34 --- /dev/null +++ b/3b977b77b/logs/2100040.out @@ -0,0 +1,48175 @@ +Model parameters: d_model 2944 ffw_size 11776 kv_size 128 n_heads 23 n_layers 36 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 2 --num-layers 36 --hidden-size 2944 --num-attention-heads 23 --kv-channels 128 --ffn-hidden-size 11776 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 1 --global-batch-size 512 --train-samples 37_792_969 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-3b977b --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 37_792_969 --lr-warmup-samples 377_930 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 10000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_3b977b --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_3b977b --load checkpoints_3b977b --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2100040.json --zero-stage 0 +START 2100040: Fri Dec 2 10:44:31 EET 2022 + 0: + 0: + 0: ======================= ROCm System Management Interface ======================= + 0: ================================= Concise Info ================================= + 0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 0: 0 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 39.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: ================================================================================ + 0: ============================= End of ROCm SMI Log ============================== +58: +58: +58: ======================= ROCm System Management Interface ======================= +58: ================================= Concise Info ================================= +58: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +58: 0 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 4 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: 6 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +58: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +58: ================================================================================ +58: ============================= End of ROCm SMI Log ============================== +56: +56: +56: ======================= ROCm System Management Interface ======================= +56: ================================= Concise Info ================================= +56: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +56: 0 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 2 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: 6 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +56: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +56: ================================================================================ +56: ============================= End of ROCm SMI Log ============================== +48: +48: +48: ======================= ROCm System Management Interface ======================= +48: ================================= Concise Info ================================= +48: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +48: 0 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 2 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 3 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 4 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: 6 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +48: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +48: ================================================================================ +48: ============================= End of ROCm SMI Log ============================== + 1: + 1: + 1: ======================= ROCm System Management Interface ======================= + 1: ================================= Concise Info ================================= + 1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 1: 0 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 2 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 34.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: ================================================================================ + 1: ============================= End of ROCm SMI Log ============================== +52: +52: +52: ======================= ROCm System Management Interface ======================= +52: ================================= Concise Info ================================= +52: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +52: 0 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 2 38.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 4 37.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: 6 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +52: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +52: ================================================================================ +52: ============================= End of ROCm SMI Log ============================== + 2: + 2: + 2: ======================= ROCm System Management Interface ======================= + 2: ================================= Concise Info ================================= + 2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 2: 0 41.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 43.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: ================================================================================ + 2: ============================= End of ROCm SMI Log ============================== +57: +57: +57: ======================= ROCm System Management Interface ======================= +57: ================================= Concise Info ================================= +57: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +57: 0 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 2 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 4 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +57: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +57: ================================================================================ +57: ============================= End of ROCm SMI Log ============================== +39: +39: +39: ======================= ROCm System Management Interface ======================= +39: ================================= Concise Info ================================= +39: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +39: 0 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 4 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: 6 39.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +39: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +39: ================================================================================ +39: ============================= End of ROCm SMI Log ============================== +24: +24: +24: ======================= ROCm System Management Interface ======================= +24: ================================= Concise Info ================================= +24: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +24: 0 41.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= End of ROCm SMI Log ============================== +51: +51: +51: ======================= ROCm System Management Interface ======================= +51: ================================= Concise Info ================================= +51: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +51: 0 44.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 2 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 4 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: 6 37.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +51: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +51: ================================================================================ +51: ============================= End of ROCm SMI Log ============================== +25: +25: +25: ======================= ROCm System Management Interface ======================= +25: ================================= Concise Info ================================= +25: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +25: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= End of ROCm SMI Log ============================== +62: +62: +62: ======================= ROCm System Management Interface ======================= +62: ================================= Concise Info ================================= +62: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +62: 0 45.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 2 38.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: 6 38.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +62: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +62: ================================================================================ +62: ============================= End of ROCm SMI Log ============================== +61: +61: +61: ======================= ROCm System Management Interface ======================= +61: ================================= Concise Info ================================= +61: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +61: 0 44.0c 101.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 2 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 4 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: 6 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +61: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +61: ================================================================================ +61: ============================= End of ROCm SMI Log ============================== +59: +59: +59: ======================= ROCm System Management Interface ======================= +59: ================================= Concise Info ================================= +59: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +59: 0 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 2 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 4 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: 6 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +59: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +59: ================================================================================ +59: ============================= End of ROCm SMI Log ============================== +60: +60: +60: ======================= ROCm System Management Interface ======================= +60: ================================= Concise Info ================================= +60: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +60: 0 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 2 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 4 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: 6 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +60: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +60: ================================================================================ +60: ============================= End of ROCm SMI Log ============================== +63: +63: +63: ======================= ROCm System Management Interface ======================= +63: ================================= Concise Info ================================= +63: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +63: 0 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 2 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 4 40.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: 6 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +63: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +63: ================================================================================ +63: ============================= End of ROCm SMI Log ============================== +38: +38: +38: ======================= ROCm System Management Interface ======================= +38: ================================= Concise Info ================================= +38: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +38: 0 43.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 2 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 4 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: 6 36.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +38: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +38: ================================================================================ +38: ============================= End of ROCm SMI Log ============================== +19: +19: +19: ======================= ROCm System Management Interface ======================= +19: ================================= Concise Info ================================= +19: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +19: 0 41.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= End of ROCm SMI Log ============================== +55: +55: +55: ======================= ROCm System Management Interface ======================= +55: ================================= Concise Info ================================= +55: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +55: 0 48.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 4 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: 6 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +55: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +55: ================================================================================ +55: ============================= End of ROCm SMI Log ============================== +21: +21: +21: ======================= ROCm System Management Interface ======================= +21: ================================= Concise Info ================================= +21: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +21: 0 45.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 40.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 47.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: ================================================================================ +21: ============================= End of ROCm SMI Log ============================== + 6: + 6: + 6: ======================= ROCm System Management Interface ======================= + 6: ================================= Concise Info ================================= + 6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 6: 0 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 40.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 46.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: ================================================================================ + 6: ============================= End of ROCm SMI Log ============================== + 7: + 7: + 7: ======================= ROCm System Management Interface ======================= + 7: ================================= Concise Info ================================= + 7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 7: 0 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: ================================================================================ + 7: ============================= End of ROCm SMI Log ============================== +26: +26: +26: ======================= ROCm System Management Interface ======================= +26: ================================= Concise Info ================================= +26: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +26: 0 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 40.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: ================================================================================ +26: ============================= End of ROCm SMI Log ============================== + 9: + 9: + 9: ======================= ROCm System Management Interface ======================= + 9: ================================= Concise Info ================================= + 9: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 9: 0 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= End of ROCm SMI Log ============================== +10: +10: +10: ======================= ROCm System Management Interface ======================= +10: ================================= Concise Info ================================= +10: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +10: 0 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 37.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 38.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= End of ROCm SMI Log ============================== +20: +20: +20: ======================= ROCm System Management Interface ======================= +20: ================================= Concise Info ================================= +20: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +20: 0 47.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: ================================================================================ +20: ============================= End of ROCm SMI Log ============================== +46: +46: +46: ======================= ROCm System Management Interface ======================= +46: ================================= Concise Info ================================= +46: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +46: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 2 43.0c 102.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 4 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: 6 35.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +46: 7 36.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +46: ================================================================================ +46: ============================= End of ROCm SMI Log ============================== + 4: + 4: + 4: ======================= ROCm System Management Interface ======================= + 4: ================================= Concise Info ================================= + 4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 4: 0 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: ================================================================================ + 4: ============================= End of ROCm SMI Log ============================== +23: +23: +23: ======================= ROCm System Management Interface ======================= +23: ================================= Concise Info ================================= +23: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +23: 0 45.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= End of ROCm SMI Log ============================== +40: +40: +40: ======================= ROCm System Management Interface ======================= +40: ================================= Concise Info ================================= +40: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +40: 0 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 2 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 4 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: 6 36.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +40: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +40: ================================================================================ +40: ============================= End of ROCm SMI Log ============================== +44: +44: +44: ======================= ROCm System Management Interface ======================= +44: ================================= Concise Info ================================= +44: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +44: 0 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 2 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 4 36.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: 6 44.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +44: 7 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +44: ================================================================================ +44: ============================= End of ROCm SMI Log ============================== + 5: + 5: + 5: ======================= ROCm System Management Interface ======================= + 5: ================================= Concise Info ================================= + 5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 5: 0 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 2 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: ================================================================================ + 5: ============================= End of ROCm SMI Log ============================== +29: +29: +29: ======================= ROCm System Management Interface ======================= +29: ================================= Concise Info ================================= +29: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +29: 0 44.0c 103.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 37.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= End of ROCm SMI Log ============================== +42: +42: +42: ======================= ROCm System Management Interface ======================= +42: ================================= Concise Info ================================= +42: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +42: 0 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 2 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 4 46.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: 6 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +42: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +42: ================================================================================ +42: ============================= End of ROCm SMI Log ============================== +18: +18: +18: ======================= ROCm System Management Interface ======================= +18: ================================= Concise Info ================================= +18: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +18: 0 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= End of ROCm SMI Log ============================== +45: +45: +45: ======================= ROCm System Management Interface ======================= +45: ================================= Concise Info ================================= +45: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +45: 0 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 4 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: 6 36.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +45: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +45: ================================================================================ +45: ============================= End of ROCm SMI Log ============================== +47: +47: +47: ======================= ROCm System Management Interface ======================= +47: ================================= Concise Info ================================= +47: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +47: 0 39.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 4 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: 6 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +47: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +47: ================================================================================ +47: ============================= End of ROCm SMI Log ============================== +11: +11: +11: ======================= ROCm System Management Interface ======================= +11: ================================= Concise Info ================================= +11: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +11: 0 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 38.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 41.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= End of ROCm SMI Log ============================== +22: +22: +22: ======================= ROCm System Management Interface ======================= +22: ================================= Concise Info ================================= +22: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +22: 0 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= End of ROCm SMI Log ============================== +41: +41: +41: ======================= ROCm System Management Interface ======================= +41: ================================= Concise Info ================================= +41: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +41: 0 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 2 36.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 4 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: 6 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +41: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +41: ================================================================================ +41: ============================= End of ROCm SMI Log ============================== +30: +30: +30: ======================= ROCm System Management Interface ======================= +30: ================================= Concise Info ================================= +30: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +30: 0 42.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: ================================================================================ +30: ============================= End of ROCm SMI Log ============================== +43: +43: +43: ======================= ROCm System Management Interface ======================= +43: ================================= Concise Info ================================= +43: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +43: 0 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 2 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 4 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: 6 36.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +43: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +43: ================================================================================ +43: ============================= End of ROCm SMI Log ============================== + 3: + 3: + 3: ======================= ROCm System Management Interface ======================= + 3: ================================= Concise Info ================================= + 3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 3: 0 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 2 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: ================================================================================ + 3: ============================= End of ROCm SMI Log ============================== +14: +14: +14: ======================= ROCm System Management Interface ======================= +14: ================================= Concise Info ================================= +14: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +14: 0 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 41.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 46.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= End of ROCm SMI Log ============================== +17: +17: +17: ======================= ROCm System Management Interface ======================= +17: ================================= Concise Info ================================= +17: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +17: 0 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 38.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= End of ROCm SMI Log ============================== +28: +28: +28: ======================= ROCm System Management Interface ======================= +28: ================================= Concise Info ================================= +28: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +28: 0 44.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 35.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= End of ROCm SMI Log ============================== +31: +31: +31: ======================= ROCm System Management Interface ======================= +31: ================================= Concise Info ================================= +31: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +31: 0 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= End of ROCm SMI Log ============================== +27: +27: +27: ======================= ROCm System Management Interface ======================= +27: ================================= Concise Info ================================= +27: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +27: 0 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 38.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 44.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: ================================================================================ +27: ============================= End of ROCm SMI Log ============================== +36: +36: +36: ======================= ROCm System Management Interface ======================= +36: ================================= Concise Info ================================= +36: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +36: 0 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 2 33.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 4 42.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: 6 36.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +36: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +36: ================================================================================ +36: ============================= End of ROCm SMI Log ============================== +32: +32: +32: ======================= ROCm System Management Interface ======================= +32: ================================= Concise Info ================================= +32: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +32: 0 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 2 37.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 4 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: 6 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +32: 7 37.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +32: ================================================================================ +32: ============================= End of ROCm SMI Log ============================== +34: +34: +34: ======================= ROCm System Management Interface ======================= +34: ================================= Concise Info ================================= +34: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +34: 0 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 2 50.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 4 36.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: 6 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +34: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +34: ================================================================================ +34: ============================= End of ROCm SMI Log ============================== +16: +16: +16: ======================= ROCm System Management Interface ======================= +16: ================================= Concise Info ================================= +16: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +16: 0 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 37.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: ================================================================================ +16: ============================= End of ROCm SMI Log ============================== +49: +49: +49: ======================= ROCm System Management Interface ======================= +49: ================================= Concise Info ================================= +49: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +49: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 2 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 4 38.0c 101.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: 6 40.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +49: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +49: ================================================================================ +49: ============================= End of ROCm SMI Log ============================== +37: +37: +37: ======================= ROCm System Management Interface ======================= +37: ================================= Concise Info ================================= +37: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +37: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 2 39.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 4 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +37: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +37: ================================================================================ +37: ============================= End of ROCm SMI Log ============================== +35: +35: +35: ======================= ROCm System Management Interface ======================= +35: ================================= Concise Info ================================= +35: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +35: 0 43.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 2 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 4 39.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: 6 50.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +35: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +35: ================================================================================ +35: ============================= End of ROCm SMI Log ============================== +50: +50: +50: ======================= ROCm System Management Interface ======================= +50: ================================= Concise Info ================================= +50: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +50: 0 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 2 37.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 4 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: 6 36.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +50: 7 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +50: ================================================================================ +50: ============================= End of ROCm SMI Log ============================== +15: +15: +15: ======================= ROCm System Management Interface ======================= +15: ================================= Concise Info ================================= +15: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +15: 0 48.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 38.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= End of ROCm SMI Log ============================== +13: +13: +13: ======================= ROCm System Management Interface ======================= +13: ================================= Concise Info ================================= +13: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +13: 0 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 4 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: ================================================================================ +13: ============================= End of ROCm SMI Log ============================== +33: +33: +33: ======================= ROCm System Management Interface ======================= +33: ================================= Concise Info ================================= +33: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +33: 0 39.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 2 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 4 41.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: 6 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +33: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +33: ================================================================================ +33: ============================= End of ROCm SMI Log ============================== + 8: + 8: + 8: ======================= ROCm System Management Interface ======================= + 8: ================================= Concise Info ================================= + 8: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 8: 0 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 37.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= End of ROCm SMI Log ============================== +53: +53: +53: ======================= ROCm System Management Interface ======================= +53: ================================= Concise Info ================================= +53: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +53: 0 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 2 44.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 4 35.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: 6 35.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +53: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +53: ================================================================================ +53: ============================= End of ROCm SMI Log ============================== +12: +12: +12: ======================= ROCm System Management Interface ======================= +12: ================================= Concise Info ================================= +12: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +12: 0 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= End of ROCm SMI Log ============================== +54: +54: +54: ======================= ROCm System Management Interface ======================= +54: ================================= Concise Info ================================= +54: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +54: 0 42.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 2 38.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 4 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: 6 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +54: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +54: ================================================================================ +54: ============================= End of ROCm SMI Log ============================== +33: Launching on nid006490 (33/64), master nid005274 port 9999, GPUs 8, CUDA: True + 0: Launching on nid005274 (0/64), master nid005274 port 9999, GPUs 8, CUDA: True +58: Launching on nid006882 (58/64), master nid005274 port 9999, GPUs 8, CUDA: True +53: Launching on nid006877 (53/64), master nid005274 port 9999, GPUs 8, CUDA: True +52: Launching on nid006876 (52/64), master nid005274 port 9999, GPUs 8, CUDA: True +48: Launching on nid006872 (48/64), master nid005274 port 9999, GPUs 8, CUDA: True +56: Launching on nid006880 (56/64), master nid005274 port 9999, GPUs 8, CUDA: True + 2: Launching on nid005276 (2/64), master nid005274 port 9999, GPUs 8, CUDA: True +54: Launching on nid006878 (54/64), master nid005274 port 9999, GPUs 8, CUDA: True +62: Launching on nid006886 (62/64), master nid005274 port 9999, GPUs 8, CUDA: True +60: Launching on nid006884 (60/64), master nid005274 port 9999, GPUs 8, CUDA: True +24: Launching on nid005410 (24/64), master nid005274 port 9999, GPUs 8, CUDA: True +26: Launching on nid006483 (26/64), master nid005274 port 9999, GPUs 8, CUDA: True +10: Launching on nid005284 (10/64), master nid005274 port 9999, GPUs 8, CUDA: True +46: Launching on nid006870 (46/64), master nid005274 port 9999, GPUs 8, CUDA: True + 6: Launching on nid005280 (6/64), master nid005274 port 9999, GPUs 8, CUDA: True +20: Launching on nid005406 (20/64), master nid005274 port 9999, GPUs 8, CUDA: True +40: Launching on nid006497 (40/64), master nid005274 port 9999, GPUs 8, CUDA: True +38: Launching on nid006495 (38/64), master nid005274 port 9999, GPUs 8, CUDA: True + 1: Launching on nid005275 (1/64), master nid005274 port 9999, GPUs 8, CUDA: True +57: Launching on nid006881 (57/64), master nid005274 port 9999, GPUs 8, CUDA: True +51: Launching on nid006875 (51/64), master nid005274 port 9999, GPUs 8, CUDA: True +55: Launching on nid006879 (55/64), master nid005274 port 9999, GPUs 8, CUDA: True +61: Launching on nid006885 (61/64), master nid005274 port 9999, GPUs 8, CUDA: True +63: Launching on nid006887 (63/64), master nid005274 port 9999, GPUs 8, CUDA: True +59: Launching on nid006883 (59/64), master nid005274 port 9999, GPUs 8, CUDA: True +25: Launching on nid005411 (25/64), master nid005274 port 9999, GPUs 8, CUDA: True +21: Launching on nid005407 (21/64), master nid005274 port 9999, GPUs 8, CUDA: True + 7: Launching on nid005281 (7/64), master nid005274 port 9999, GPUs 8, CUDA: True + 9: Launching on nid005283 (9/64), master nid005274 port 9999, GPUs 8, CUDA: True +39: Launching on nid006496 (39/64), master nid005274 port 9999, GPUs 8, CUDA: True +19: Launching on nid005405 (19/64), master nid005274 port 9999, GPUs 8, CUDA: True +23: Launching on nid005409 (23/64), master nid005274 port 9999, GPUs 8, CUDA: True +45: Launching on nid006869 (45/64), master nid005274 port 9999, GPUs 8, CUDA: True + 4: Launching on nid005278 (4/64), master nid005274 port 9999, GPUs 8, CUDA: True +44: Launching on nid006501 (44/64), master nid005274 port 9999, GPUs 8, CUDA: True +42: Launching on nid006499 (42/64), master nid005274 port 9999, GPUs 8, CUDA: True +18: Launching on nid005292 (18/64), master nid005274 port 9999, GPUs 8, CUDA: True +22: Launching on nid005408 (22/64), master nid005274 port 9999, GPUs 8, CUDA: True +30: Launching on nid006487 (30/64), master nid005274 port 9999, GPUs 8, CUDA: True +28: Launching on nid006485 (28/64), master nid005274 port 9999, GPUs 8, CUDA: True +32: Launching on nid006489 (32/64), master nid005274 port 9999, GPUs 8, CUDA: True +16: Launching on nid005290 (16/64), master nid005274 port 9999, GPUs 8, CUDA: True +34: Launching on nid006491 (34/64), master nid005274 port 9999, GPUs 8, CUDA: True +36: Launching on nid006493 (36/64), master nid005274 port 9999, GPUs 8, CUDA: True +14: Launching on nid005288 (14/64), master nid005274 port 9999, GPUs 8, CUDA: True +50: Launching on nid006874 (50/64), master nid005274 port 9999, GPUs 8, CUDA: True +12: Launching on nid005286 (12/64), master nid005274 port 9999, GPUs 8, CUDA: True + 8: Launching on nid005282 (8/64), master nid005274 port 9999, GPUs 8, CUDA: True + 5: Launching on nid005279 (5/64), master nid005274 port 9999, GPUs 8, CUDA: True +11: Launching on nid005285 (11/64), master nid005274 port 9999, GPUs 8, CUDA: True +47: Launching on nid006871 (47/64), master nid005274 port 9999, GPUs 8, CUDA: True +43: Launching on nid006500 (43/64), master nid005274 port 9999, GPUs 8, CUDA: True +41: Launching on nid006498 (41/64), master nid005274 port 9999, GPUs 8, CUDA: True +17: Launching on nid005291 (17/64), master nid005274 port 9999, GPUs 8, CUDA: True + 3: Launching on nid005277 (3/64), master nid005274 port 9999, GPUs 8, CUDA: True +29: Launching on nid006486 (29/64), master nid005274 port 9999, GPUs 8, CUDA: True +31: Launching on nid006488 (31/64), master nid005274 port 9999, GPUs 8, CUDA: True +49: Launching on nid006873 (49/64), master nid005274 port 9999, GPUs 8, CUDA: True +37: Launching on nid006494 (37/64), master nid005274 port 9999, GPUs 8, CUDA: True +15: Launching on nid005289 (15/64), master nid005274 port 9999, GPUs 8, CUDA: True +35: Launching on nid006492 (35/64), master nid005274 port 9999, GPUs 8, CUDA: True +27: Launching on nid006484 (27/64), master nid005274 port 9999, GPUs 8, CUDA: True +13: Launching on nid005287 (13/64), master nid005274 port 9999, GPUs 8, CUDA: True + 0: using world size: 512, data-parallel-size: 256, tensor-model-parallel size: 1, pipeline-model-parallel size: 2 + 0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. + 0: using torch.bfloat16 for parameters ... + 0: ------------------------ arguments ------------------------ + 0: abort_on_unmet_fused_kernel_constraints ......... False + 0: accumulate_allreduce_grads_in_fp32 .............. True + 0: adam_beta1 ...................................... 0.9 + 0: adam_beta2 ...................................... 0.999 + 0: adam_eps ........................................ 1e-08 + 0: adlr_autoresume ................................. False + 0: adlr_autoresume_interval ........................ 1000 + 0: apply_query_key_layer_scaling ................... True + 0: apply_residual_connection_post_layernorm ........ False + 0: attention_dropout ............................... 0.1 + 0: attention_softmax_in_fp32 ....................... False + 0: bert_binary_head ................................ True + 0: bert_load ....................................... None + 0: bf16 ............................................ True + 0: bias_dropout_fusion ............................. True + 0: bias_gelu_fusion ................................ True + 0: biencoder_projection_dim ........................ 0 + 0: biencoder_shared_query_context_model ............ False + 0: block_data_path ................................. None + 0: checkpoint_activations .......................... False + 0: checkpoint_in_cpu ............................... False + 0: checkpoint_num_layers ........................... 1 + 0: clip_grad ....................................... 1.0 + 0: codecarbon_dir .................................. None + 0: consumed_train_samples .......................... 0 + 0: consumed_train_tokens ........................... 0 + 0: consumed_valid_samples .......................... 0 + 0: contigious_checkpointing ........................ False + 0: cpu_optimizer ................................... False + 0: cpu_torch_adam .................................. False + 0: curriculum_learning ............................. False + 0: data_impl ....................................... mmap + 0: data_parallel_size .............................. 256 + 0: data_path ....................................... ['/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document'] + 0: dataloader_type ................................. single + 0: DDP_impl ........................................ local + 0: decoder_seq_length .............................. None + 0: deepscale ....................................... False + 0: deepscale_config ................................ None + 0: deepspeed ....................................... True + 0: deepspeed_activation_checkpointing .............. False + 0: deepspeed_config ................................ ds_configs/2100040.json + 0: deepspeed_mpi ................................... False + 0: distribute_checkpointed_activations ............. False + 0: distributed_backend ............................. nccl + 0: embed_layernorm ................................. False + 0: embedding_path .................................. None + 0: encoder_seq_length .............................. 2048 + 0: eod_mask_loss ................................... False + 0: eval_interval ................................... 1000 + 0: eval_iters ...................................... 1 + 0: eval_only ....................................... None + 0: evidence_data_path .............................. None + 0: exit_duration_in_mins ........................... None + 0: exit_interval ................................... None + 0: ffn_hidden_size ................................. 11776 + 0: finetune ........................................ False + 0: fp16 ............................................ False + 0: fp16_lm_cross_entropy ........................... False + 0: fp32_residual_connection ........................ False + 0: gigaflos_no_embeds .............................. 0 + 0: global_batch_size ............................... 512 + 0: glu_activation .................................. None + 0: hidden_dropout .................................. 0.1 + 0: hidden_size ..................................... 2944 + 0: hysteresis ...................................... 2 + 0: ict_head_size ................................... None + 0: ict_load ........................................ None + 0: img_dim ......................................... 224 + 0: indexer_batch_size .............................. 128 + 0: indexer_log_interval ............................ 1000 + 0: inference ....................................... False + 0: init_method_std ................................. 0.02 + 0: init_method_xavier_uniform ...................... False + 0: initial_loss_scale .............................. 4294967296 + 0: kill_switch_path ................................ kill-switch-3b977b + 0: kv_channels ..................................... 128 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ checkpoints_3b977b + 0: local_rank ...................................... None + 0: log_batch_size_to_tensorboard ................... True + 0: log_interval .................................... 10 + 0: log_learning_rate_to_tensorboard ................ True + 0: log_level ....................................... None + 0: log_level_replica ............................... None + 0: log_loss_scale_to_tensorboard ................... True + 0: log_num_zeros_in_grad ........................... False + 0: log_params_norm ................................. False + 0: log_path ........................................ None + 0: log_timers_to_tensorboard ....................... True + 0: log_validation_ppl_to_tensorboard ............... True + 0: loss_on_targets_only ............................ False + 0: loss_scale ...................................... None + 0: loss_scale_window ............................... 1000 + 0: lr .............................................. 0.0002 + 0: lr_decay_iters .................................. None + 0: lr_decay_samples ................................ 37792969 + 0: lr_decay_style .................................. cosine + 0: lr_decay_tokens ................................. None + 0: lr_warmup_fraction .............................. None + 0: lr_warmup_iters ................................. 0 + 0: lr_warmup_samples ............................... 377930 + 0: make_vocab_size_divisible_by .................... 128 + 0: mask_prob ....................................... 0.15 + 0: masked_softmax_fusion ........................... True + 0: max_position_embeddings ......................... 2048 + 0: mean_noise_span_length .......................... None + 0: memory_centric_tiled_linear ..................... False + 0: merge_file ...................................... gpt2/merges.txt + 0: micro_batch_size ................................ 1 + 0: min_loss_scale .................................. 1.0 + 0: min_lr .......................................... 2e-05 + 0: mmap_warmup ..................................... False + 0: no_load_optim ................................... None + 0: no_load_rng ..................................... None + 0: no_save_optim ................................... None + 0: no_save_rng ..................................... None + 0: noise_density ................................... None + 0: num_attention_heads ............................. 23 + 0: num_channels .................................... 3 + 0: num_classes ..................................... 1000 + 0: num_layers ...................................... 36 + 0: num_layers_per_virtual_pipeline_stage ........... None + 0: num_workers ..................................... 2 + 0: onnx_safe ....................................... None + 0: openai_gelu ..................................... False + 0: optimizer ....................................... adam + 0: optimizer_fusion ................................ True + 0: override_lr_scheduler ........................... False + 0: pad_vocab_size_to ............................... None + 0: params_dtype .................................... torch.bfloat16 + 0: partition_activations ........................... False + 0: patch_dim ....................................... 16 + 0: pipeline_model_parallel_size .................... 2 + 0: position_embedding_type ......................... PositionEmbeddingType.absolute + 0: pp_partition_method ............................. None + 0: profile_backward ................................ False + 0: query_in_block_prob ............................. 0.1 + 0: rampup_batch_size ............................... None + 0: rank ............................................ 0 + 0: remote_device ................................... none + 0: reset_attention_mask ............................ False + 0: reset_position_ids .............................. False + 0: retriever_report_topk_accuracies ................ [] + 0: retriever_score_scaling ......................... False + 0: retriever_seq_length ............................ 256 + 0: reweight_loss_based_on_position_frequency ....... False + 0: sample_rate ..................................... 1.0 + 0: save ............................................ checkpoints_3b977b + 0: save_interval ................................... 10000 + 0: scatter_gather_tensors_in_pipeline .............. True + 0: scattered_embeddings ............................ False + 0: seed ............................................ 1234 + 0: seq_length ...................................... 2048 + 0: sgd_momentum .................................... 0.9 + 0: short_seq_prob .................................. 0.1 + 0: skip_train_iteration_range ...................... None + 0: split ........................................... 949,50,1 + 0: split_transformers .............................. False + 0: sync_tp_duplicated_parameters ................... False + 0: synchronize_each_layer .......................... False + 0: tensor_model_parallel_size ...................... 1 + 0: tensorboard_dir ................................. tensorboard_3b977b + 0: tensorboard_log_interval ........................ 1 + 0: tensorboard_queue_size .......................... 5 + 0: test_weighted_split_names ....................... None + 0: test_weighted_split_paths ....................... None + 0: test_weighted_split_paths_path .................. None + 0: test_weighted_split_splits ...................... None + 0: test_weighted_split_weights ..................... None + 0: tile_factor ..................................... 1 + 0: titles_data_path ................................ None + 0: tokenizer_name_or_path .......................... None + 0: tokenizer_type .................................. GPT2BPETokenizer + 0: train_iters ..................................... None + 0: train_samples ................................... 37792969 + 0: train_tokens .................................... None + 0: train_weighted_split_paths ...................... None + 0: train_weighted_split_paths_path ................. None + 0: universal_checkpoint ............................ False + 0: use_bnb_optimizer ............................... False + 0: use_checkpoint_lr_scheduler ..................... False + 0: use_contiguous_buffers_in_ddp ................... True + 0: use_cpu_initialization .......................... None + 0: use_one_sent_docs ............................... False + 0: use_pin_memory .................................. False + 0: valid_num_workers ............................... 2 + 0: valid_weighted_split_names ...................... None + 0: valid_weighted_split_paths ...................... None + 0: valid_weighted_split_paths_path ................. None + 0: valid_weighted_split_splits ..................... None + 0: valid_weighted_split_weights .................... None + 0: virtual_pipeline_model_parallel_size ............ None + 0: vocab_extra_ids ................................. 0 + 0: vocab_file ...................................... gpt2/vocab.json + 0: weight_decay .................................... 0.1 + 0: world_size ...................................... 512 + 0: zero_allgather_bucket_size ...................... 0.0 + 0: zero_contigious_gradients ....................... False + 0: zero_reduce_bucket_size ......................... 0.0 + 0: zero_reduce_scatter ............................. False + 0: zero_stage ...................................... 0 + 0: -------------------- end of arguments --------------------- + 0: setting number of micro-batches to constant 2 + 0: > building GPT2BPETokenizer tokenizer ... + 0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) + 0: DeepSpeed general environment info: + 0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] + 0: torch version .................... 1.13.0+rocm5.2 + 0: torch cuda version ............... None + 0: torch hip version ................ 5.2.21151-afdc89f8 + 0: nvcc version ..................... None + 0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] + 0: deepspeed info ................... 0.7.5, unknown, unknown + 0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 + 0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** + 0: > initializing torch distributed ... + 0: [2022-12-02 10:46:29,153] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +63: > setting tensorboard ... + 0: > initializing tensor model parallel with size 1 + 0: > initializing pipeline model parallel with size 2 + 0: > setting random seeds to 1234 ... + 0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 + 0: > compiling dataset index builder ... + 0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: make: Nothing to be done for 'default'. + 0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' + 0: >>> done with dataset index builder. Compilation time: 0.096 seconds + 0: WARNING: constraints for invoking optimized fused softmax kernel are not met. We default back to unfused kernel invocations. + 0: > compiling and loading fused kernels ... + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 87 + 0: ninja: no work to do. + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 63 + 0: [1/1] c++ scaled_masked_softmax_hip.o scaled_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_masked_softmax_cuda.so + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] + 0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] + 0: Total number of unsupported CUDA function calls: 0 + 0: + 0: + 0: Total number of replaced kernel launches: 67 + 0: [1/1] c++ layer_norm_cuda.o layer_norm_hip_kernel.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so + 0: >>> done with compiling and loading fused kernels. Compilation time: 287.436 seconds + 0: time to initialize megatron (seconds): 287.739 + 0: [after megatron is initialized] datetime: 2022-12-02 10:51:43 + 0: building GPT model ... + 0: [2022-12-02 10:51:43,813] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2022-12-02 10:51:43,814] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB + 0: [2022-12-02 10:51:43,814] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 55.84 GB, percent = 11.1% + 0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None + 0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi + 0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 + 0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63, ProcessCoord(pipe=0, data=64, model=0): 64, ProcessCoord(pipe=0, data=65, model=0): 65, ProcessCoord(pipe=0, data=66, model=0): 66, ProcessCoord(pipe=0, data=67, model=0): 67, ProcessCoord(pipe=0, data=68, model=0): 68, ProcessCoord(pipe=0, data=69, model=0): + 0: 69, ProcessCoord(pipe=0, data=70, model=0): 70, ProcessCoord(pipe=0, data=71, model=0): 71, ProcessCoord(pipe=0, data=72, model=0): 72, ProcessCoord(pipe=0, data=73, model=0): 73, ProcessCoord(pipe=0, data=74, model=0): 74, ProcessCoord(pipe=0, data=75, model=0): 75, ProcessCoord(pipe=0, data=76, model=0): 76, ProcessCoord(pipe=0, data=77, model=0): 77, ProcessCoord(pipe=0, data=78, model=0): 78, ProcessCoord(pipe=0, data=79, model=0): 79, ProcessCoord(pipe=0, data=80, model=0): 80, ProcessCoord(pipe=0, data=81, model=0): 81, ProcessCoord(pipe=0, data=82, model=0): 82, ProcessCoord(pipe=0, data=83, model=0): 83, ProcessCoord(pipe=0, data=84, model=0): 84, ProcessCoord(pipe=0, data=85, model=0): 85, ProcessCoord(pipe=0, data=86, model=0): 86, ProcessCoord(pipe=0, data=87, model=0): 87, ProcessCoord(pipe=0, data=88, model=0): 88, ProcessCoord(pipe=0, data=89, model=0): 89, ProcessCoord(pipe=0, data=90, model=0): 90, ProcessCoord(pipe=0, data=91, model=0): 91, ProcessCoord(pipe=0, data=92, model=0): 92, Process + 0: Coord(pipe=0, data=93, model=0): 93, ProcessCoord(pipe=0, data=94, model=0): 94, ProcessCoord(pipe=0, data=95, model=0): 95, ProcessCoord(pipe=0, data=96, model=0): 96, ProcessCoord(pipe=0, data=97, model=0): 97, ProcessCoord(pipe=0, data=98, model=0): 98, ProcessCoord(pipe=0, data=99, model=0): 99, ProcessCoord(pipe=0, data=100, model=0): 100, ProcessCoord(pipe=0, data=101, model=0): 101, ProcessCoord(pipe=0, data=102, model=0): 102, ProcessCoord(pipe=0, data=103, model=0): 103, ProcessCoord(pipe=0, data=104, model=0): 104, ProcessCoord(pipe=0, data=105, model=0): 105, ProcessCoord(pipe=0, data=106, model=0): 106, ProcessCoord(pipe=0, data=107, model=0): 107, ProcessCoord(pipe=0, data=108, model=0): 108, ProcessCoord(pipe=0, data=109, model=0): 109, ProcessCoord(pipe=0, data=110, model=0): 110, ProcessCoord(pipe=0, data=111, model=0): 111, ProcessCoord(pipe=0, data=112, model=0): 112, ProcessCoord(pipe=0, data=113, model=0): 113, ProcessCoord(pipe=0, data=114, model=0): 114, ProcessCoord(pipe=0, data=115, mo + 0: del=0): 115, ProcessCoord(pipe=0, data=116, model=0): 116, ProcessCoord(pipe=0, data=117, model=0): 117, ProcessCoord(pipe=0, data=118, model=0): 118, ProcessCoord(pipe=0, data=119, model=0): 119, ProcessCoord(pipe=0, data=120, model=0): 120, ProcessCoord(pipe=0, data=121, model=0): 121, ProcessCoord(pipe=0, data=122, model=0): 122, ProcessCoord(pipe=0, data=123, model=0): 123, ProcessCoord(pipe=0, data=124, model=0): 124, ProcessCoord(pipe=0, data=125, model=0): 125, ProcessCoord(pipe=0, data=126, model=0): 126, ProcessCoord(pipe=0, data=127, model=0): 127, ProcessCoord(pipe=0, data=128, model=0): 128, ProcessCoord(pipe=0, data=129, model=0): 129, ProcessCoord(pipe=0, data=130, model=0): 130, ProcessCoord(pipe=0, data=131, model=0): 131, ProcessCoord(pipe=0, data=132, model=0): 132, ProcessCoord(pipe=0, data=133, model=0): 133, ProcessCoord(pipe=0, data=134, model=0): 134, ProcessCoord(pipe=0, data=135, model=0): 135, ProcessCoord(pipe=0, data=136, model=0): 136, ProcessCoord(pipe=0, data=137, model=0): 137, + 0: ProcessCoord(pipe=0, data=138, model=0): 138, ProcessCoord(pipe=0, data=139, model=0): 139, ProcessCoord(pipe=0, data=140, model=0): 140, ProcessCoord(pipe=0, data=141, model=0): 141, ProcessCoord(pipe=0, data=142, model=0): 142, ProcessCoord(pipe=0, data=143, model=0): 143, ProcessCoord(pipe=0, data=144, model=0): 144, ProcessCoord(pipe=0, data=145, model=0): 145, ProcessCoord(pipe=0, data=146, model=0): 146, ProcessCoord(pipe=0, data=147, model=0): 147, ProcessCoord(pipe=0, data=148, model=0): 148, ProcessCoord(pipe=0, data=149, model=0): 149, ProcessCoord(pipe=0, data=150, model=0): 150, ProcessCoord(pipe=0, data=151, model=0): 151, ProcessCoord(pipe=0, data=152, model=0): 152, ProcessCoord(pipe=0, data=153, model=0): 153, ProcessCoord(pipe=0, data=154, model=0): 154, ProcessCoord(pipe=0, data=155, model=0): 155, ProcessCoord(pipe=0, data=156, model=0): 156, ProcessCoord(pipe=0, data=157, model=0): 157, ProcessCoord(pipe=0, data=158, model=0): 158, ProcessCoord(pipe=0, data=159, model=0): 159, ProcessCoor + 0: d(pipe=0, data=160, model=0): 160, ProcessCoord(pipe=0, data=161, model=0): 161, ProcessCoord(pipe=0, data=162, model=0): 162, ProcessCoord(pipe=0, data=163, model=0): 163, ProcessCoord(pipe=0, data=164, model=0): 164, ProcessCoord(pipe=0, data=165, model=0): 165, ProcessCoord(pipe=0, data=166, model=0): 166, ProcessCoord(pipe=0, data=167, model=0): 167, ProcessCoord(pipe=0, data=168, model=0): 168, ProcessCoord(pipe=0, data=169, model=0): 169, ProcessCoord(pipe=0, data=170, model=0): 170, ProcessCoord(pipe=0, data=171, model=0): 171, ProcessCoord(pipe=0, data=172, model=0): 172, ProcessCoord(pipe=0, data=173, model=0): 173, ProcessCoord(pipe=0, data=174, model=0): 174, ProcessCoord(pipe=0, data=175, model=0): 175, ProcessCoord(pipe=0, data=176, model=0): 176, ProcessCoord(pipe=0, data=177, model=0): 177, ProcessCoord(pipe=0, data=178, model=0): 178, ProcessCoord(pipe=0, data=179, model=0): 179, ProcessCoord(pipe=0, data=180, model=0): 180, ProcessCoord(pipe=0, data=181, model=0): 181, ProcessCoord(pipe=0, da + 0: ta=182, model=0): 182, ProcessCoord(pipe=0, data=183, model=0): 183, ProcessCoord(pipe=0, data=184, model=0): 184, ProcessCoord(pipe=0, data=185, model=0): 185, ProcessCoord(pipe=0, data=186, model=0): 186, ProcessCoord(pipe=0, data=187, model=0): 187, ProcessCoord(pipe=0, data=188, model=0): 188, ProcessCoord(pipe=0, data=189, model=0): 189, ProcessCoord(pipe=0, data=190, model=0): 190, ProcessCoord(pipe=0, data=191, model=0): 191, ProcessCoord(pipe=0, data=192, model=0): 192, ProcessCoord(pipe=0, data=193, model=0): 193, ProcessCoord(pipe=0, data=194, model=0): 194, ProcessCoord(pipe=0, data=195, model=0): 195, ProcessCoord(pipe=0, data=196, model=0): 196, ProcessCoord(pipe=0, data=197, model=0): 197, ProcessCoord(pipe=0, data=198, model=0): 198, ProcessCoord(pipe=0, data=199, model=0): 199, ProcessCoord(pipe=0, data=200, model=0): 200, ProcessCoord(pipe=0, data=201, model=0): 201, ProcessCoord(pipe=0, data=202, model=0): 202, ProcessCoord(pipe=0, data=203, model=0): 203, ProcessCoord(pipe=0, data=204, mode + 0: l=0): 204, ProcessCoord(pipe=0, data=205, model=0): 205, ProcessCoord(pipe=0, data=206, model=0): 206, ProcessCoord(pipe=0, data=207, model=0): 207, ProcessCoord(pipe=0, data=208, model=0): 208, ProcessCoord(pipe=0, data=209, model=0): 209, ProcessCoord(pipe=0, data=210, model=0): 210, ProcessCoord(pipe=0, data=211, model=0): 211, ProcessCoord(pipe=0, data=212, model=0): 212, ProcessCoord(pipe=0, data=213, model=0): 213, ProcessCoord(pipe=0, data=214, model=0): 214, ProcessCoord(pipe=0, data=215, model=0): 215, ProcessCoord(pipe=0, data=216, model=0): 216, ProcessCoord(pipe=0, data=217, model=0): 217, ProcessCoord(pipe=0, data=218, model=0): 218, ProcessCoord(pipe=0, data=219, model=0): 219, ProcessCoord(pipe=0, data=220, model=0): 220, ProcessCoord(pipe=0, data=221, model=0): 221, ProcessCoord(pipe=0, data=222, model=0): 222, ProcessCoord(pipe=0, data=223, model=0): 223, ProcessCoord(pipe=0, data=224, model=0): 224, ProcessCoord(pipe=0, data=225, model=0): 225, ProcessCoord(pipe=0, data=226, model=0): 226, P + 0: rocessCoord(pipe=0, data=227, model=0): 227, ProcessCoord(pipe=0, data=228, model=0): 228, ProcessCoord(pipe=0, data=229, model=0): 229, ProcessCoord(pipe=0, data=230, model=0): 230, ProcessCoord(pipe=0, data=231, model=0): 231, ProcessCoord(pipe=0, data=232, model=0): 232, ProcessCoord(pipe=0, data=233, model=0): 233, ProcessCoord(pipe=0, data=234, model=0): 234, ProcessCoord(pipe=0, data=235, model=0): 235, ProcessCoord(pipe=0, data=236, model=0): 236, ProcessCoord(pipe=0, data=237, model=0): 237, ProcessCoord(pipe=0, data=238, model=0): 238, ProcessCoord(pipe=0, data=239, model=0): 239, ProcessCoord(pipe=0, data=240, model=0): 240, ProcessCoord(pipe=0, data=241, model=0): 241, ProcessCoord(pipe=0, data=242, model=0): 242, ProcessCoord(pipe=0, data=243, model=0): 243, ProcessCoord(pipe=0, data=244, model=0): 244, ProcessCoord(pipe=0, data=245, model=0): 245, ProcessCoord(pipe=0, data=246, model=0): 246, ProcessCoord(pipe=0, data=247, model=0): 247, ProcessCoord(pipe=0, data=248, model=0): 248, ProcessCoord( + 0: pipe=0, data=249, model=0): 249, ProcessCoord(pipe=0, data=250, model=0): 250, ProcessCoord(pipe=0, data=251, model=0): 251, ProcessCoord(pipe=0, data=252, model=0): 252, ProcessCoord(pipe=0, data=253, model=0): 253, ProcessCoord(pipe=0, data=254, model=0): 254, ProcessCoord(pipe=0, data=255, model=0): 255, ProcessCoord(pipe=1, data=0, model=0): 256, ProcessCoord(pipe=1, data=1, model=0): 257, ProcessCoord(pipe=1, data=2, model=0): 258, ProcessCoord(pipe=1, data=3, model=0): 259, ProcessCoord(pipe=1, data=4, model=0): 260, ProcessCoord(pipe=1, data=5, model=0): 261, ProcessCoord(pipe=1, data=6, model=0): 262, ProcessCoord(pipe=1, data=7, model=0): 263, ProcessCoord(pipe=1, data=8, model=0): 264, ProcessCoord(pipe=1, data=9, model=0): 265, ProcessCoord(pipe=1, data=10, model=0): 266, ProcessCoord(pipe=1, data=11, model=0): 267, ProcessCoord(pipe=1, data=12, model=0): 268, ProcessCoord(pipe=1, data=13, model=0): 269, ProcessCoord(pipe=1, data=14, model=0): 270, ProcessCoord(pipe=1, data=15, model=0): 271, Proce + 0: ssCoord(pipe=1, data=16, model=0): 272, ProcessCoord(pipe=1, data=17, model=0): 273, ProcessCoord(pipe=1, data=18, model=0): 274, ProcessCoord(pipe=1, data=19, model=0): 275, ProcessCoord(pipe=1, data=20, model=0): 276, ProcessCoord(pipe=1, data=21, model=0): 277, ProcessCoord(pipe=1, data=22, model=0): 278, ProcessCoord(pipe=1, data=23, model=0): 279, ProcessCoord(pipe=1, data=24, model=0): 280, ProcessCoord(pipe=1, data=25, model=0): 281, ProcessCoord(pipe=1, data=26, model=0): 282, ProcessCoord(pipe=1, data=27, model=0): 283, ProcessCoord(pipe=1, data=28, model=0): 284, ProcessCoord(pipe=1, data=29, model=0): 285, ProcessCoord(pipe=1, data=30, model=0): 286, ProcessCoord(pipe=1, data=31, model=0): 287, ProcessCoord(pipe=1, data=32, model=0): 288, ProcessCoord(pipe=1, data=33, model=0): 289, ProcessCoord(pipe=1, data=34, model=0): 290, ProcessCoord(pipe=1, data=35, model=0): 291, ProcessCoord(pipe=1, data=36, model=0): 292, ProcessCoord(pipe=1, data=37, model=0): 293, ProcessCoord(pipe=1, data=38, model=0): + 0: 294, ProcessCoord(pipe=1, data=39, model=0): 295, ProcessCoord(pipe=1, data=40, model=0): 296, ProcessCoord(pipe=1, data=41, model=0): 297, ProcessCoord(pipe=1, data=42, model=0): 298, ProcessCoord(pipe=1, data=43, model=0): 299, ProcessCoord(pipe=1, data=44, model=0): 300, ProcessCoord(pipe=1, data=45, model=0): 301, ProcessCoord(pipe=1, data=46, model=0): 302, ProcessCoord(pipe=1, data=47, model=0): 303, ProcessCoord(pipe=1, data=48, model=0): 304, ProcessCoord(pipe=1, data=49, model=0): 305, ProcessCoord(pipe=1, data=50, model=0): 306, ProcessCoord(pipe=1, data=51, model=0): 307, ProcessCoord(pipe=1, data=52, model=0): 308, ProcessCoord(pipe=1, data=53, model=0): 309, ProcessCoord(pipe=1, data=54, model=0): 310, ProcessCoord(pipe=1, data=55, model=0): 311, ProcessCoord(pipe=1, data=56, model=0): 312, ProcessCoord(pipe=1, data=57, model=0): 313, ProcessCoord(pipe=1, data=58, model=0): 314, ProcessCoord(pipe=1, data=59, model=0): 315, ProcessCoord(pipe=1, data=60, model=0): 316, ProcessCoord(pipe=1, data=61 + 0: , model=0): 317, ProcessCoord(pipe=1, data=62, model=0): 318, ProcessCoord(pipe=1, data=63, model=0): 319, ProcessCoord(pipe=1, data=64, model=0): 320, ProcessCoord(pipe=1, data=65, model=0): 321, ProcessCoord(pipe=1, data=66, model=0): 322, ProcessCoord(pipe=1, data=67, model=0): 323, ProcessCoord(pipe=1, data=68, model=0): 324, ProcessCoord(pipe=1, data=69, model=0): 325, ProcessCoord(pipe=1, data=70, model=0): 326, ProcessCoord(pipe=1, data=71, model=0): 327, ProcessCoord(pipe=1, data=72, model=0): 328, ProcessCoord(pipe=1, data=73, model=0): 329, ProcessCoord(pipe=1, data=74, model=0): 330, ProcessCoord(pipe=1, data=75, model=0): 331, ProcessCoord(pipe=1, data=76, model=0): 332, ProcessCoord(pipe=1, data=77, model=0): 333, ProcessCoord(pipe=1, data=78, model=0): 334, ProcessCoord(pipe=1, data=79, model=0): 335, ProcessCoord(pipe=1, data=80, model=0): 336, ProcessCoord(pipe=1, data=81, model=0): 337, ProcessCoord(pipe=1, data=82, model=0): 338, ProcessCoord(pipe=1, data=83, model=0): 339, ProcessCoord(pipe + 0: =1, data=84, model=0): 340, ProcessCoord(pipe=1, data=85, model=0): 341, ProcessCoord(pipe=1, data=86, model=0): 342, ProcessCoord(pipe=1, data=87, model=0): 343, ProcessCoord(pipe=1, data=88, model=0): 344, ProcessCoord(pipe=1, data=89, model=0): 345, ProcessCoord(pipe=1, data=90, model=0): 346, ProcessCoord(pipe=1, data=91, model=0): 347, ProcessCoord(pipe=1, data=92, model=0): 348, ProcessCoord(pipe=1, data=93, model=0): 349, ProcessCoord(pipe=1, data=94, model=0): 350, ProcessCoord(pipe=1, data=95, model=0): 351, ProcessCoord(pipe=1, data=96, model=0): 352, ProcessCoord(pipe=1, data=97, model=0): 353, ProcessCoord(pipe=1, data=98, model=0): 354, ProcessCoord(pipe=1, data=99, model=0): 355, ProcessCoord(pipe=1, data=100, model=0): 356, ProcessCoord(pipe=1, data=101, model=0): 357, ProcessCoord(pipe=1, data=102, model=0): 358, ProcessCoord(pipe=1, data=103, model=0): 359, ProcessCoord(pipe=1, data=104, model=0): 360, ProcessCoord(pipe=1, data=105, model=0): 361, ProcessCoord(pipe=1, data=106, model=0): 362, + 0: ProcessCoord(pipe=1, data=107, model=0): 363, ProcessCoord(pipe=1, data=108, model=0): 364, ProcessCoord(pipe=1, data=109, model=0): 365, ProcessCoord(pipe=1, data=110, model=0): 366, ProcessCoord(pipe=1, data=111, model=0): 367, ProcessCoord(pipe=1, data=112, model=0): 368, ProcessCoord(pipe=1, data=113, model=0): 369, ProcessCoord(pipe=1, data=114, model=0): 370, ProcessCoord(pipe=1, data=115, model=0): 371, ProcessCoord(pipe=1, data=116, model=0): 372, ProcessCoord(pipe=1, data=117, model=0): 373, ProcessCoord(pipe=1, data=118, model=0): 374, ProcessCoord(pipe=1, data=119, model=0): 375, ProcessCoord(pipe=1, data=120, model=0): 376, ProcessCoord(pipe=1, data=121, model=0): 377, ProcessCoord(pipe=1, data=122, model=0): 378, ProcessCoord(pipe=1, data=123, model=0): 379, ProcessCoord(pipe=1, data=124, model=0): 380, ProcessCoord(pipe=1, data=125, model=0): 381, ProcessCoord(pipe=1, data=126, model=0): 382, ProcessCoord(pipe=1, data=127, model=0): 383, ProcessCoord(pipe=1, data=128, model=0): 384, ProcessCoor + 0: d(pipe=1, data=129, model=0): 385, ProcessCoord(pipe=1, data=130, model=0): 386, ProcessCoord(pipe=1, data=131, model=0): 387, ProcessCoord(pipe=1, data=132, model=0): 388, ProcessCoord(pipe=1, data=133, model=0): 389, ProcessCoord(pipe=1, data=134, model=0): 390, ProcessCoord(pipe=1, data=135, model=0): 391, ProcessCoord(pipe=1, data=136, model=0): 392, ProcessCoord(pipe=1, data=137, model=0): 393, ProcessCoord(pipe=1, data=138, model=0): 394, ProcessCoord(pipe=1, data=139, model=0): 395, ProcessCoord(pipe=1, data=140, model=0): 396, ProcessCoord(pipe=1, data=141, model=0): 397, ProcessCoord(pipe=1, data=142, model=0): 398, ProcessCoord(pipe=1, data=143, model=0): 399, ProcessCoord(pipe=1, data=144, model=0): 400, ProcessCoord(pipe=1, data=145, model=0): 401, ProcessCoord(pipe=1, data=146, model=0): 402, ProcessCoord(pipe=1, data=147, model=0): 403, ProcessCoord(pipe=1, data=148, model=0): 404, ProcessCoord(pipe=1, data=149, model=0): 405, ProcessCoord(pipe=1, data=150, model=0): 406, ProcessCoord(pipe=1, da + 0: ta=151, model=0): 407, ProcessCoord(pipe=1, data=152, model=0): 408, ProcessCoord(pipe=1, data=153, model=0): 409, ProcessCoord(pipe=1, data=154, model=0): 410, ProcessCoord(pipe=1, data=155, model=0): 411, ProcessCoord(pipe=1, data=156, model=0): 412, ProcessCoord(pipe=1, data=157, model=0): 413, ProcessCoord(pipe=1, data=158, model=0): 414, ProcessCoord(pipe=1, data=159, model=0): 415, ProcessCoord(pipe=1, data=160, model=0): 416, ProcessCoord(pipe=1, data=161, model=0): 417, ProcessCoord(pipe=1, data=162, model=0): 418, ProcessCoord(pipe=1, data=163, model=0): 419, ProcessCoord(pipe=1, data=164, model=0): 420, ProcessCoord(pipe=1, data=165, model=0): 421, ProcessCoord(pipe=1, data=166, model=0): 422, ProcessCoord(pipe=1, data=167, model=0): 423, ProcessCoord(pipe=1, data=168, model=0): 424, ProcessCoord(pipe=1, data=169, model=0): 425, ProcessCoord(pipe=1, data=170, model=0): 426, ProcessCoord(pipe=1, data=171, model=0): 427, ProcessCoord(pipe=1, data=172, model=0): 428, ProcessCoord(pipe=1, data=173, mode + 0: l=0): 429, ProcessCoord(pipe=1, data=174, model=0): 430, ProcessCoord(pipe=1, data=175, model=0): 431, ProcessCoord(pipe=1, data=176, model=0): 432, ProcessCoord(pipe=1, data=177, model=0): 433, ProcessCoord(pipe=1, data=178, model=0): 434, ProcessCoord(pipe=1, data=179, model=0): 435, ProcessCoord(pipe=1, data=180, model=0): 436, ProcessCoord(pipe=1, data=181, model=0): 437, ProcessCoord(pipe=1, data=182, model=0): 438, ProcessCoord(pipe=1, data=183, model=0): 439, ProcessCoord(pipe=1, data=184, model=0): 440, ProcessCoord(pipe=1, data=185, model=0): 441, ProcessCoord(pipe=1, data=186, model=0): 442, ProcessCoord(pipe=1, data=187, model=0): 443, ProcessCoord(pipe=1, data=188, model=0): 444, ProcessCoord(pipe=1, data=189, model=0): 445, ProcessCoord(pipe=1, data=190, model=0): 446, ProcessCoord(pipe=1, data=191, model=0): 447, ProcessCoord(pipe=1, data=192, model=0): 448, ProcessCoord(pipe=1, data=193, model=0): 449, ProcessCoord(pipe=1, data=194, model=0): 450, ProcessCoord(pipe=1, data=195, model=0): 451, P + 0: rocessCoord(pipe=1, data=196, model=0): 452, ProcessCoord(pipe=1, data=197, model=0): 453, ProcessCoord(pipe=1, data=198, model=0): 454, ProcessCoord(pipe=1, data=199, model=0): 455, ProcessCoord(pipe=1, data=200, model=0): 456, ProcessCoord(pipe=1, data=201, model=0): 457, ProcessCoord(pipe=1, data=202, model=0): 458, ProcessCoord(pipe=1, data=203, model=0): 459, ProcessCoord(pipe=1, data=204, model=0): 460, ProcessCoord(pipe=1, data=205, model=0): 461, ProcessCoord(pipe=1, data=206, model=0): 462, ProcessCoord(pipe=1, data=207, model=0): 463, ProcessCoord(pipe=1, data=208, model=0): 464, ProcessCoord(pipe=1, data=209, model=0): 465, ProcessCoord(pipe=1, data=210, model=0): 466, ProcessCoord(pipe=1, data=211, model=0): 467, ProcessCoord(pipe=1, data=212, model=0): 468, ProcessCoord(pipe=1, data=213, model=0): 469, ProcessCoord(pipe=1, data=214, model=0): 470, ProcessCoord(pipe=1, data=215, model=0): 471, ProcessCoord(pipe=1, data=216, model=0): 472, ProcessCoord(pipe=1, data=217, model=0): 473, ProcessCoord( + 0: pipe=1, data=218, model=0): 474, ProcessCoord(pipe=1, data=219, model=0): 475, ProcessCoord(pipe=1, data=220, model=0): 476, ProcessCoord(pipe=1, data=221, model=0): 477, ProcessCoord(pipe=1, data=222, model=0): 478, ProcessCoord(pipe=1, data=223, model=0): 479, ProcessCoord(pipe=1, data=224, model=0): 480, ProcessCoord(pipe=1, data=225, model=0): 481, ProcessCoord(pipe=1, data=226, model=0): 482, ProcessCoord(pipe=1, data=227, model=0): 483, ProcessCoord(pipe=1, data=228, model=0): 484, ProcessCoord(pipe=1, data=229, model=0): 485, ProcessCoord(pipe=1, data=230, model=0): 486, ProcessCoord(pipe=1, data=231, model=0): 487, ProcessCoord(pipe=1, data=232, model=0): 488, ProcessCoord(pipe=1, data=233, model=0): 489, ProcessCoord(pipe=1, data=234, model=0): 490, ProcessCoord(pipe=1, data=235, model=0): 491, ProcessCoord(pipe=1, data=236, model=0): 492, ProcessCoord(pipe=1, data=237, model=0): 493, ProcessCoord(pipe=1, data=238, model=0): 494, ProcessCoord(pipe=1, data=239, model=0): 495, ProcessCoord(pipe=1, data + 0: =240, model=0): 496, ProcessCoord(pipe=1, data=241, model=0): 497, ProcessCoord(pipe=1, data=242, model=0): 498, ProcessCoord(pipe=1, data=243, model=0): 499, ProcessCoord(pipe=1, data=244, model=0): 500, ProcessCoord(pipe=1, data=245, model=0): 501, ProcessCoord(pipe=1, data=246, model=0): 502, ProcessCoord(pipe=1, data=247, model=0): 503, ProcessCoord(pipe=1, data=248, model=0): 504, ProcessCoord(pipe=1, data=249, model=0): 505, ProcessCoord(pipe=1, data=250, model=0): 506, ProcessCoord(pipe=1, data=251, model=0): 507, ProcessCoord(pipe=1, data=252, model=0): 508, ProcessCoord(pipe=1, data=253, model=0): 509, ProcessCoord(pipe=1, data=254, model=0): 510, ProcessCoord(pipe=1, data=255, model=0): 511} + 0: [2022-12-02 10:52:02,103] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer + 0: stage=0 layers=21 + 0: 0: _to_float16 + 0: 1: EmbeddingPipe + 0: 2: + 0: 3: ParallelTransformerLayerPipe + 0: 4: ParallelTransformerLayerPipe + 0: 5: ParallelTransformerLayerPipe + 0: 6: ParallelTransformerLayerPipe + 0: 7: ParallelTransformerLayerPipe + 0: 8: ParallelTransformerLayerPipe + 0: 9: ParallelTransformerLayerPipe + 0: 10: ParallelTransformerLayerPipe + 0: 11: ParallelTransformerLayerPipe + 0: 12: ParallelTransformerLayerPipe + 0: 13: ParallelTransformerLayerPipe + 0: 14: ParallelTransformerLayerPipe + 0: 15: ParallelTransformerLayerPipe + 0: 16: ParallelTransformerLayerPipe + 0: 17: ParallelTransformerLayerPipe + 0: 18: ParallelTransformerLayerPipe + 0: 19: ParallelTransformerLayerPipe + 0: 20: ParallelTransformerLayerPipe + 0: stage=1 layers=22 + 0: 21: ParallelTransformerLayerPipe + 0: 22: ParallelTransformerLayerPipe + 0: 23: ParallelTransformerLayerPipe + 0: 24: ParallelTransformerLayerPipe + 0: 25: ParallelTransformerLayerPipe + 0: 26: ParallelTransformerLayerPipe + 0: 27: ParallelTransformerLayerPipe + 0: 28: ParallelTransformerLayerPipe + 0: 29: ParallelTransformerLayerPipe + 0: 30: ParallelTransformerLayerPipe + 0: 31: ParallelTransformerLayerPipe + 0: 32: ParallelTransformerLayerPipe + 0: 33: ParallelTransformerLayerPipe + 0: 34: ParallelTransformerLayerPipe + 0: 35: ParallelTransformerLayerPipe + 0: 36: ParallelTransformerLayerPipe + 0: 37: ParallelTransformerLayerPipe + 0: 38: ParallelTransformerLayerPipe + 0: 39: undo + 0: 40: MixedFusedLayerNorm + 0: 41: EmbeddingPipe + 0: 42: float16_to_fp32 + 0: loss: CrossEntropy + 0: [2022-12-02 10:52:07,525] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2022-12-02 10:52:07,525] [INFO] [utils.py:828:see_memory_usage] MA 3.8 GB Max_MA 3.8 GB CA 3.89 GB Max_CA 4 GB + 0: [2022-12-02 10:52:07,525] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 56.35 GB, percent = 11.2% + 0: setting training iterations to 73814 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2022-12-02 10:52:07,527] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2022-12-02 10:52:25,099] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2022-12-02 10:52:25,100] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2022-12-02 10:52:25,100] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2022-12-02 10:52:25,106] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2022-12-02 10:52:25,106] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2022-12-02 10:52:25,147] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2022-12-02 10:52:25,147] [INFO] [utils.py:828:see_memory_usage] MA 3.78 GB Max_MA 3.81 GB CA 3.9 GB Max_CA 4 GB + 0: [2022-12-02 10:52:25,147] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.18 GB, percent = 11.4% +13: ninja: no work to do. + 0: ninja: no work to do. +13: Time to load utils op: 0.12197113037109375 seconds +13: Time to load utils op: 0.12198233604431152 seconds +13: Time to load utils op: 0.12164616584777832 seconds +13: Time to load utils op: 0.12145042419433594 seconds +13: Time to load utils op: 0.12264156341552734 seconds +13: Time to load utils op: 0.12232494354248047 seconds +13: Time to load utils op: 0.12142109870910645 seconds +13: Time to load utils op: 0.4198639392852783 seconds + 9: Time to load utils op: 0.1221463680267334 secondsTime to load utils op: 0.12218523025512695 seconds + 9: Time to load utils op: 0.1221628189086914 seconds + 9: + 9: Time to load utils op: 0.1221609115600586 seconds + 9: Time to load utils op: 0.12216854095458984 seconds + 9: Time to load utils op: 0.12217473983764648 seconds + 9: Time to load utils op: 0.12218332290649414 seconds + 9: Time to load utils op: 0.12222695350646973 seconds +50: Time to load utils op: 0.24735331535339355 seconds +50: Time to load utils op: 0.24736547470092773 seconds +50: Time to load utils op: 0.24739408493041992 secondsTime to load utils op: 0.24739432334899902 seconds +50: +50: Time to load utils op: 0.2474195957183838 secondsTime to load utils op: 0.2474193572998047 seconds +50: +50: Time to load utils op: 0.24742960929870605 secondsTime to load utils op: 0.24744224548339844 seconds +50: +58: Time to load utils op: 0.24320483207702637 seconds +58: Time to load utils op: 0.2431032657623291 secondsTime to load utils op: 0.2431485652923584 seconds +58: Time to load utils op: 0.24307894706726074 seconds +58: +58: Time to load utils op: 0.24370527267456055 seconds + 7: Time to load utils op: 0.4249396324157715 seconds + 6: Time to load utils op: 0.4256010055541992 seconds +27: Time to load utils op: 0.10924959182739258 seconds +27: Time to load utils op: 0.1099395751953125 secondsTime to load utils op: 0.10928988456726074 seconds +27: +51: Time to load utils op: 0.25002050399780273 seconds +51: Time to load utils op: 0.2500114440917969 seconds +27: Time to load utils op: 0.1092984676361084 seconds +27: Time to load utils op: 0.10983514785766602 secondsTime to load utils op: 0.4124910831451416 seconds +27: +27: Time to load utils op: 0.10933494567871094 seconds +27: Time to load utils op: 0.10962748527526855 seconds +51: Time to load utils op: 0.2500293254852295 seconds +51: Time to load utils op: 0.2500746250152588 secondsTime to load utils op: 0.2500760555267334 seconds +51: +51: Time to load utils op: 0.2500636577606201 seconds +51: Time to load utils op: 0.2500901222229004 secondsTime to load utils op: 0.250089168548584 seconds +51: + 5: Time to load utils op: 0.13420438766479492 seconds + 5: Time to load utils op: 0.13425922393798828 seconds + 5: Time to load utils op: 0.13423466682434082 seconds + 5: Time to load utils op: 0.1342630386352539 seconds + 5: Time to load utils op: 0.1342628002166748 secondsTime to load utils op: 0.13426852226257324 seconds + 5: + 5: Time to load utils op: 0.13428020477294922 seconds + 5: Time to load utils op: 0.13431262969970703 seconds + 0: Time to load utils op: 0.1459493637084961 seconds +14: Time to load utils op: 0.1260063648223877 seconds +14: Time to load utils op: 0.12599706649780273 seconds +14: Time to load utils op: 0.12601351737976074 seconds +14: Time to load utils op: 0.12601232528686523 seconds +14: Time to load utils op: 0.12601590156555176 seconds +14: Time to load utils op: 0.1260547637939453 secondsTime to load utils op: 0.1260523796081543 secondsTime to load utils op: 0.1260213851928711 seconds +14: + 4: Time to load utils op: 0.13769936561584473 seconds +14: + 4: Time to load utils op: 0.13776326179504395 seconds + 4: Time to load utils op: 0.13774466514587402 seconds + 4: Time to load utils op: 0.1377861499786377 seconds + 4: Time to load utils op: 0.13778328895568848 seconds + 4: Time to load utils op: 0.13781023025512695 secondsTime to load utils op: 0.1377873420715332 seconds + 4: + 4: Time to load utils op: 0.137800931930542 seconds + 8: Time to load utils op: 0.13397479057312012 seconds + 8: Time to load utils op: 0.13396453857421875 seconds + 8: Time to load utils op: 0.13401150703430176 seconds + 8: Time to load utils op: 0.13398051261901855 secondsTime to load utils op: 0.1340162754058838 seconds + 8: + 8: Time to load utils op: 0.13399028778076172 seconds + 8: Time to load utils op: 0.13401103019714355 seconds + 8: Time to load utils op: 0.13400697708129883 seconds +11: Time to load utils op: 0.1313490867614746 seconds +11: Time to load utils op: 0.13139081001281738 seconds +11: Time to load utils op: 0.13136768341064453 seconds +11: Time to load utils op: 0.13138675689697266 seconds +11: Time to load utils op: 0.1314380168914795 seconds +11: Time to load utils op: 0.13142704963684082 secondsTime to load utils op: 0.13142752647399902 seconds +11: Time to load utils op: 0.13144636154174805 seconds +11: +15: Time to load utils op: 0.1262366771697998 seconds +15: Time to load utils op: 0.1262359619140625 seconds +15: Time to load utils op: 0.12629485130310059 seconds +15: Time to load utils op: 0.12631535530090332 seconds +15: Time to load utils op: 0.12631964683532715 seconds +15: Time to load utils op: 0.12635517120361328 seconds +15: Time to load utils op: 0.12633585929870605 seconds +15: Time to load utils op: 0.12634634971618652 seconds +21: Time to load utils op: 0.11868476867675781 seconds +21: Time to load utils op: 0.11870455741882324 seconds +21: Time to load utils op: 0.11871814727783203 seconds +21: Time to load utils op: 0.11872196197509766 seconds +21: Time to load utils op: 0.11874628067016602 seconds +21: Time to load utils op: 0.11872982978820801 seconds +21: Time to load utils op: 0.11876368522644043 secondsTime to load utils op: 0.1187582015991211 seconds +21: +22: Time to load utils op: 0.11907410621643066 seconds +22: Time to load utils op: 0.11911559104919434 seconds +22: Time to load utils op: 0.11908578872680664 seconds +22: Time to load utils op: 0.11910438537597656 seconds +22: Time to load utils op: 0.11915731430053711 seconds +22: Time to load utils op: 0.11913204193115234 secondsTime to load utils op: 0.11912846565246582 seconds +22: +22: Time to load utils op: 0.11913061141967773 seconds +18: Time to load utils op: 0.12517237663269043 seconds +18: Time to load utils op: 0.12518525123596191 seconds +18: Time to load utils op: 0.1252148151397705 secondsTime to load utils op: 0.12519335746765137 seconds +18: +18: Time to load utils op: 0.12522673606872559 secondsTime to load utils op: 0.1252284049987793 seconds +18: +18: Time to load utils op: 0.12519383430480957 seconds +18: Time to load utils op: 0.1252155303955078 seconds +16: Time to load utils op: 0.13270044326782227 seconds +16: Time to load utils op: 0.13218045234680176 seconds +16: Time to load utils op: 0.13219618797302246 seconds +16: Time to load utils op: 0.43421244621276855 seconds +16: Time to load utils op: 0.13222765922546387 secondsTime to load utils op: 0.1322314739227295 seconds +16: +16: Time to load utils op: 0.13228178024291992 secondsTime to load utils op: 0.13227224349975586 seconds +16: +19: Time to load utils op: 0.12871336936950684 seconds +19: Time to load utils op: 0.432861328125 seconds +19: Time to load utils op: 0.12876677513122559 seconds +19: Time to load utils op: 0.1289520263671875 seconds +19: Time to load utils op: 0.12874317169189453 seconds +19: Time to load utils op: 0.12878870964050293 secondsTime to load utils op: 0.12876081466674805 seconds +19: +19: Time to load utils op: 0.12941646575927734 seconds +29: Time to load utils op: 0.11251187324523926 seconds +29: Time to load utils op: 0.11251997947692871 seconds +24: Time to load utils op: 0.11986398696899414 seconds +24: Time to load utils op: 0.11984705924987793 seconds +25: Time to load utils op: 0.11689209938049316 secondsTime to load utils op: 0.11689209938049316 seconds +25: +29: Time to load utils op: 0.11252045631408691 secondsTime to load utils op: 0.11255574226379395 seconds +29: +29: Time to load utils op: 0.1125333309173584 secondsTime to load utils op: 0.1125180721282959 seconds +29: +29: Time to load utils op: 0.11257624626159668 seconds +29: Time to load utils op: 0.11255145072937012 seconds +24: Time to load utils op: 0.11986374855041504 seconds +25: Time to load utils op: 0.1169130802154541 seconds +24: Time to load utils op: 0.11986041069030762 seconds +25: Time to load utils op: 0.11691617965698242 secondsTime to load utils op: 0.11692142486572266 seconds +25: +24: Time to load utils op: 0.11987161636352539 secondsTime to load utils op: 0.11987495422363281 seconds +24: +25: Time to load utils op: 0.1169581413269043 seconds +24: Time to load utils op: 0.11991453170776367 seconds +25: Time to load utils op: 0.11694645881652832 seconds +24: Time to load utils op: 0.11989355087280273 seconds +25: Time to load utils op: 0.11694741249084473 seconds +20: Time to load utils op: 0.12435722351074219 seconds +20: Time to load utils op: 0.12433743476867676 seconds +20: Time to load utils op: 0.12437629699707031 seconds +20: Time to load utils op: 0.12438726425170898 seconds +20: Time to load utils op: 0.12437081336975098 seconds +20: Time to load utils op: 0.12437677383422852 seconds +20: Time to load utils op: 0.12438488006591797 seconds +20: Time to load utils op: 0.12439274787902832 seconds +28: Time to load utils op: 0.12091469764709473 seconds +28: Time to load utils op: 0.12106442451477051 seconds +28: Time to load utils op: 0.12107586860656738 seconds +28: Time to load utils op: 0.12097477912902832 secondsTime to load utils op: 0.1206657886505127 seconds +28: +28: Time to load utils op: 0.12038493156433105 seconds +28: Time to load utils op: 0.11966848373413086 seconds +28: Time to load utils op: 0.12043595314025879 seconds +17: Time to load utils op: 0.1332836151123047 seconds +17: Time to load utils op: 0.13332915306091309 seconds +17: Time to load utils op: 0.13382601737976074 seconds +17: Time to load utils op: 0.13336682319641113 seconds +17: Time to load utils op: 0.13443946838378906 secondsTime to load utils op: 0.13337230682373047 seconds +17: +17: Time to load utils op: 0.13338088989257812 secondsTime to load utils op: 0.13456201553344727 seconds +17: +26: Time to load utils op: 0.1186988353729248 secondsTime to load utils op: 0.11871051788330078 seconds +26: +26: Time to load utils op: 0.11870241165161133 seconds +10: Time to load utils op: 0.13833951950073242 seconds +10: Time to load utils op: 0.13836121559143066 seconds +26: Time to load utils op: 0.11874127388000488 seconds +26: Time to load utils op: 0.11870789527893066 seconds +10: Time to load utils op: 0.13839983940124512 seconds +26: Time to load utils op: 0.11875486373901367 secondsTime to load utils op: 0.1187276840209961 seconds +26: +10: Time to load utils op: 0.13841032981872559 secondsTime to load utils op: 0.1384105682373047 seconds +10: +26: Time to load utils op: 0.11877584457397461 seconds +10: Time to load utils op: 0.13843393325805664 seconds +10: Time to load utils op: 0.13843464851379395 seconds +10: Time to load utils op: 0.13842391967773438 seconds +12: Time to load utils op: 0.1364598274230957 seconds +23: Time to load utils op: 0.1233675479888916 seconds +12: Time to load utils op: 0.13644647598266602 seconds +12: Time to load utils op: 0.13648772239685059 seconds +23: Time to load utils op: 0.12336540222167969 seconds +23: Time to load utils op: 0.12337398529052734 seconds +12: Time to load utils op: 0.13651537895202637 seconds +23: Time to load utils op: 0.12338757514953613 seconds +12: Time to load utils op: 0.1365196704864502 secondsTime to load utils op: 0.13651704788208008 seconds +12: +23: Time to load utils op: 0.12339663505554199 seconds +23: Time to load utils op: 0.12340927124023438 secondsTime to load utils op: 0.1234123706817627 seconds +23: +12: Time to load utils op: 0.13648033142089844 seconds +23: Time to load utils op: 0.12341904640197754 seconds +30: Time to load utils op: 0.11366939544677734 seconds +30: Time to load utils op: 0.11368036270141602 seconds +12: Time to load utils op: 0.13651561737060547 seconds +30: Time to load utils op: 0.11371135711669922 seconds +30: Time to load utils op: 0.11371850967407227 seconds +30: Time to load utils op: 0.11375641822814941 secondsTime to load utils op: 0.11375188827514648 secondsTime to load utils op: 0.1137542724609375 seconds +30: +30: +30: Time to load utils op: 0.11375904083251953 seconds +31: Time to load utils op: 0.11465573310852051 secondsTime to load utils op: 0.11466598510742188 seconds +31: +31: Time to load utils op: 0.11468958854675293 secondsTime to load utils op: 0.11469674110412598 seconds +31: +31: Time to load utils op: 0.1147150993347168 secondsTime to load utils op: 0.1146996021270752 seconds +31: +31: Time to load utils op: 0.11474394798278809 secondsTime to load utils op: 0.11470913887023926 seconds +31: +34: Time to load utils op: 0.4095580577850342 seconds +39: Time to load utils op: 0.40911078453063965 seconds +43: Time to load utils op: 0.4096803665161133 seconds +34: Time to load utils op: 0.3027503490447998 seconds +34: Time to load utils op: 0.30270981788635254 seconds +44: Time to load utils op: 0.40967392921447754 seconds +34: Time to load utils op: 0.30320239067077637 seconds +34: Time to load utils op: 0.30353474617004395 seconds +34: Time to load utils op: 0.3037879467010498 seconds +34: Time to load utils op: 0.30377984046936035 seconds +34: Time to load utils op: 0.3038673400878906 seconds +48: Time to load utils op: 0.40970563888549805 seconds +32: Time to load utils op: 0.30924296379089355 secondsTime to load utils op: 0.30910778045654297 seconds +32: +32: Time to load utils op: 0.30901217460632324 seconds +32: Time to load utils op: 0.30897092819213867 seconds +32: Time to load utils op: 0.3091466426849365 seconds +32: Time to load utils op: 0.3091895580291748 seconds +32: Time to load utils op: 0.3091428279876709 seconds +39: Time to load utils op: 0.302445650100708 seconds +39: Time to load utils op: 0.3023064136505127 seconds +39: Time to load utils op: 0.30293869972229004 seconds +52: Time to load utils op: 0.40911436080932617 seconds +39: Time to load utils op: 0.30302882194519043 seconds +39: Time to load utils op: 0.3032362461090088 seconds +39: Time to load utils op: 0.30341267585754395 secondsTime to load utils op: 0.30350279808044434 seconds +39: +53: Time to load utils op: 0.40909528732299805 seconds + 0: Time to load utils op: 0.40422487258911133 seconds +43: Time to load utils op: 0.3025174140930176 secondsTime to load utils op: 0.3027045726776123 seconds +43: +43: Time to load utils op: 0.3023972511291504 seconds +43: Time to load utils op: 0.30267786979675293 seconds +58: Time to load utils op: 0.4040055274963379 seconds +43: Time to load utils op: 0.30245089530944824 seconds +43: Time to load utils op: 0.3026316165924072 seconds +43: Time to load utils op: 0.3030576705932617 seconds +33: Time to load utils op: 0.3109269142150879 seconds +33: Time to load utils op: 0.31096482276916504 seconds +33: Time to load utils op: 0.31096911430358887 seconds +33: Time to load utils op: 0.3109889030456543 seconds +33: Time to load utils op: 0.3110048770904541 seconds +33: Time to load utils op: 0.31101346015930176 seconds +33: Time to load utils op: 0.31101298332214355 secondsTime to load utils op: 0.3110082149505615 seconds +33: +44: Time to load utils op: 0.302919864654541 seconds +44: Time to load utils op: 0.3030698299407959 seconds +44: Time to load utils op: 0.3036212921142578 seconds +44: Time to load utils op: 0.30355191230773926 secondsTime to load utils op: 0.30396103858947754 seconds +44: +44: Time to load utils op: 0.3039562702178955 seconds +44: Time to load utils op: 0.3041219711303711 seconds +36: Time to load utils op: 0.3115222454071045 seconds +36: Time to load utils op: 0.31159472465515137 seconds +36: Time to load utils op: 0.3115503787994385 seconds +36: Time to load utils op: 0.31160974502563477 secondsTime to load utils op: 0.3115811347961426 secondsTime to load utils op: 0.31159400939941406 seconds +36: +36: +36: Time to load utils op: 0.31162261962890625 seconds +36: Time to load utils op: 0.311614990234375 seconds +35: Time to load utils op: 0.3119845390319824 secondsTime to load utils op: 0.3119816780090332 secondsTime to load utils op: 0.3119518756866455 secondsTime to load utils op: 0.3119816780090332 seconds +35: +35: +35: +35: Time to load utils op: 0.3119971752166748 secondsTime to load utils op: 0.3119959831237793 secondsTime to load utils op: 0.31200432777404785 seconds +35: +35: Time to load utils op: 0.3120126724243164 seconds +35: +37: Time to load utils op: 0.31159520149230957 seconds +37: Time to load utils op: 0.31160807609558105 seconds +37: Time to load utils op: 0.31162118911743164 seconds +37: Time to load utils op: 0.3116419315338135 seconds +37: Time to load utils op: 0.31163811683654785 seconds +37: Time to load utils op: 0.31168365478515625 secondsTime to load utils op: 0.3116610050201416 seconds +37: +37: Time to load utils op: 0.311694860458374 seconds +48: Time to load utils op: 0.30280160903930664 seconds +48: Time to load utils op: 0.3030507564544678 seconds +48: Time to load utils op: 0.3024439811706543 seconds +48: Time to load utils op: 0.3025960922241211 seconds +48: Time to load utils op: 0.30273866653442383 seconds +48: Time to load utils op: 0.30345749855041504 seconds +48: Time to load utils op: 0.30336761474609375 seconds +38: Time to load utils op: 0.3125951290130615 seconds +38: Time to load utils op: 0.3125927448272705 seconds +60: Time to load utils op: 0.4101142883300781 seconds +38: Time to load utils op: 0.3126251697540283 seconds +38: Time to load utils op: 0.3126239776611328 seconds +38: Time to load utils op: 0.31264591217041016 secondsTime to load utils op: 0.312671422958374 secondsTime to load utils op: 0.31263184547424316 seconds +38: +38: +38: Time to load utils op: 0.3126866817474365 seconds +61: Time to load utils op: 0.4092824459075928 seconds +63: Time to load utils op: 0.4094672203063965 seconds +40: Time to load utils op: 0.3126099109649658 secondsTime to load utils op: 0.31261563301086426 seconds +40: +41: Time to load utils op: 0.3115990161895752 seconds +40: Time to load utils op: 0.31262898445129395 seconds +40: Time to load utils op: 0.3126697540283203 seconds +40: Time to load utils op: 0.3126816749572754 seconds +40: Time to load utils op: 0.31267476081848145 seconds +41: Time to load utils op: 0.3116457462310791 seconds +40: Time to load utils op: 0.3126671314239502 seconds +40: Time to load utils op: 0.3127100467681885 seconds +41: Time to load utils op: 0.31163835525512695 seconds +62: Time to load utils op: 0.4097573757171631 seconds +41: Time to load utils op: 0.31165075302124023 seconds +41: Time to load utils op: 0.3116898536682129 seconds +41: Time to load utils op: 0.3116621971130371 seconds +41: Time to load utils op: 0.3116798400878906 secondsTime to load utils op: 0.3116910457611084 seconds +41: +32: Time to load utils op: 0.40424275398254395 seconds +52: Time to load utils op: 0.3030433654785156 seconds +52: Time to load utils op: 0.30236077308654785 seconds +52: Time to load utils op: 0.30309343338012695 seconds +52: Time to load utils op: 0.30335545539855957 secondsTime to load utils op: 0.30323314666748047 seconds +52: +52: Time to load utils op: 0.3034019470214844 seconds +52: Time to load utils op: 0.3035008907318115 seconds +53: Time to load utils op: 0.3027031421661377 seconds +42: Time to load utils op: 0.3115806579589844 secondsTime to load utils op: 0.31159400939941406 seconds +42: +42: Time to load utils op: 0.311603307723999 secondsTime to load utils op: 0.3115687370300293 seconds +53: Time to load utils op: 0.30281496047973633 seconds +42: +42: Time to load utils op: 0.31157350540161133 seconds +42: Time to load utils op: 0.311572790145874 seconds +42: Time to load utils op: 0.3115835189819336 seconds +42: Time to load utils op: 0.3116288185119629 seconds +53: Time to load utils op: 0.302661657333374 seconds +53: Time to load utils op: 0.30335378646850586 seconds +53: Time to load utils op: 0.30313849449157715 seconds +53: Time to load utils op: 0.3032104969024658 seconds +53: Time to load utils op: 0.30359578132629395 seconds +46: Time to load utils op: 0.31160402297973633 seconds +46: Time to load utils op: 0.3115825653076172 secondsTime to load utils op: 0.31160640716552734 seconds +46: Time to load utils op: 0.31160640716552734 seconds +46: +46: Time to load utils op: 0.3116159439086914 seconds +46: Time to load utils op: 0.3116481304168701 secondsTime to load utils op: 0.31165528297424316 seconds +46: Time to load utils op: 0.3116772174835205 seconds +46: +45: Time to load utils op: 0.31183481216430664 seconds +45: Time to load utils op: 0.31186914443969727 seconds +45: Time to load utils op: 0.3119063377380371 secondsTime to load utils op: 0.31187963485717773 seconds +45: +45: Time to load utils op: 0.31194305419921875 secondsTime to load utils op: 0.3119039535522461 secondsTime to load utils op: 0.3119235038757324 seconds +45: +45: Time to load utils op: 0.31192541122436523 seconds +45: +47: Time to load utils op: 0.31082820892333984 seconds +47: Time to load utils op: 0.31084251403808594 seconds +47: Time to load utils op: 0.3108363151550293 seconds +47: Time to load utils op: 0.3108503818511963 seconds +47: Time to load utils op: 0.31085824966430664 seconds +47: Time to load utils op: 0.3108837604522705 seconds +47: Time to load utils op: 0.3108863830566406 seconds +47: Time to load utils op: 0.31087565422058105 seconds +49: Time to load utils op: 0.3115577697753906 seconds +49: Time to load utils op: 0.3115885257720947 seconds +49: Time to load utils op: 0.31160783767700195 seconds +49: Time to load utils op: 0.31162309646606445 seconds +49: Time to load utils op: 0.31162405014038086 seconds +58: Time to load utils op: 0.30380868911743164 seconds +58: Time to load utils op: 0.3037886619567871 seconds +49: Time to load utils op: 0.31162238121032715 secondsTime to load utils op: 0.31162238121032715 secondsTime to load utils op: 0.31163597106933594 seconds +49: +49: + 0: Time to load utils op: 0.2028048038482666 seconds + 0: Time to load utils op: 0.2030045986175537 seconds + 0: Time to load utils op: 0.2032637596130371 seconds + 0: Time to load utils op: 0.20336270332336426 seconds + 0: Time to load utils op: 0.20361065864562988 seconds + 0: Time to load utils op: 0.2034893035888672 seconds +60: Time to load utils op: 0.3025820255279541 seconds +60: Time to load utils op: 0.30254364013671875 seconds +60: Time to load utils op: 0.3028852939605713 seconds +60: Time to load utils op: 0.3029782772064209 secondsTime to load utils op: 0.30290985107421875 seconds +60: +60: Time to load utils op: 0.3031005859375 seconds +60: Time to load utils op: 0.3033726215362549 seconds +61: Time to load utils op: 0.30287694931030273 seconds +61: Time to load utils op: 0.3025782108306885 seconds +61: Time to load utils op: 0.3029015064239502 seconds +61: Time to load utils op: 0.3027961254119873 seconds +61: Time to load utils op: 0.3030831813812256 seconds +61: Time to load utils op: 0.30313825607299805 seconds +61: Time to load utils op: 0.30330705642700195 seconds +62: Time to load utils op: 0.3028099536895752 seconds +62: Time to load utils op: 0.3027329444885254 seconds +62: Time to load utils op: 0.3023250102996826 seconds +62: Time to load utils op: 0.3031039237976074 seconds +62: Time to load utils op: 0.3031470775604248 seconds +62: Time to load utils op: 0.30333685874938965 secondsTime to load utils op: 0.30333709716796875 seconds +62: +63: Time to load utils op: 0.3040165901184082 secondsTime to load utils op: 0.30353641510009766 seconds +63: +63: Time to load utils op: 0.3028686046600342 seconds +63: Time to load utils op: 0.30287957191467285 seconds +63: Time to load utils op: 0.3030250072479248 seconds +63: Time to load utils op: 0.30323219299316406 seconds +63: Time to load utils op: 0.3036191463470459 seconds +54: Time to load utils op: 0.3115661144256592 seconds +54: Time to load utils op: 0.311582088470459 seconds +54: Time to load utils op: 0.3115882873535156 secondsTime to load utils op: 0.31159162521362305 secondsTime to load utils op: 0.3116004467010498 seconds +54: +54: +54: Time to load utils op: 0.3116419315338135 seconds +54: Time to load utils op: 0.3116321563720703 secondsTime to load utils op: 0.31162476539611816 seconds +54: +55: Time to load utils op: 0.3121802806854248 secondsTime to load utils op: 0.312178373336792 seconds +55: +55: Time to load utils op: 0.3121819496154785 seconds +55: Time to load utils op: 0.3122584819793701 secondsTime to load utils op: 0.3122243881225586 seconds +55: Time to load utils op: 0.31221652030944824 seconds +55: +55: Time to load utils op: 0.3122682571411133 seconds +55: Time to load utils op: 0.3122696876525879 seconds + 7: Time to load utils op: 0.20273208618164062 seconds + 7: Time to load utils op: 0.20310235023498535 seconds + 7: Time to load utils op: 0.2031867504119873 seconds +56: Time to load utils op: 0.3118259906768799 seconds +56: Time to load utils op: 0.31186842918395996 seconds +56: Time to load utils op: 0.3118770122528076 seconds +56: Time to load utils op: 0.3119175434112549 seconds +56: Time to load utils op: 0.3118906021118164 secondsTime to load utils op: 0.31191086769104004 seconds +56: +56: Time to load utils op: 0.3119168281555176 secondsTime to load utils op: 0.3119373321533203 seconds +56: + 7: Time to load utils op: 0.20380759239196777 seconds + 7: Time to load utils op: 0.20302224159240723 seconds + 6: Time to load utils op: 0.20354866981506348 seconds + 7: Time to load utils op: 0.20354604721069336 seconds + 6: Time to load utils op: 0.2035682201385498 seconds + 7: Time to load utils op: 0.2039954662322998 seconds + 6: Time to load utils op: 0.20369720458984375 seconds + 6: Time to load utils op: 0.20421648025512695 seconds + 6: Time to load utils op: 0.20393610000610352 seconds + 6: Time to load utils op: 0.20407485961914062 seconds + 6: Time to load utils op: 0.20416021347045898 seconds +57: Time to load utils op: 0.31215643882751465 seconds +57: Time to load utils op: 0.31217098236083984 seconds +57: Time to load utils op: 0.3121933937072754 seconds +57: Time to load utils op: 0.31218671798706055 seconds +57: Time to load utils op: 0.3122081756591797 seconds +57: Time to load utils op: 0.3122220039367676 seconds +57: Time to load utils op: 0.31220364570617676 seconds +57: Time to load utils op: 0.3122568130493164 seconds +59: Time to load utils op: 0.3115556240081787 seconds +59: Time to load utils op: 0.31156420707702637 seconds +59: Time to load utils op: 0.31158971786499023 seconds +59: Time to load utils op: 0.3115839958190918 seconds +59: Time to load utils op: 0.311603307723999 secondsTime to load utils op: 0.31159019470214844 seconds +59: +59: Time to load utils op: 0.31159281730651855 seconds +59: Time to load utils op: 0.31159472465515137 seconds + 2: Time to load utils op: 0.21128177642822266 seconds + 1: Time to load utils op: 0.21101808547973633 secondsTime to load utils op: 0.21101617813110352 seconds + 1: + 2: Time to load utils op: 0.2112727165222168 seconds + 1: Time to load utils op: 0.21104216575622559 seconds + 2: Time to load utils op: 0.21132469177246094 seconds + 1: Time to load utils op: 0.21106457710266113 secondsTime to load utils op: 0.21107816696166992 seconds + 1: + 1: Time to load utils op: 0.211073637008667 secondsTime to load utils op: 0.21109437942504883 seconds + 1: + 2: Time to load utils op: 0.21132159233093262 seconds + 1: Time to load utils op: 0.2111203670501709 seconds + 2: Time to load utils op: 0.2113358974456787 seconds + 2: Time to load utils op: 0.21136760711669922 secondsTime to load utils op: 0.21134161949157715 seconds + 2: Time to load utils op: 0.2113652229309082 seconds + 2: + 3: Time to load utils op: 0.21104788780212402 secondsTime to load utils op: 0.21108531951904297 seconds + 3: + 3: Time to load utils op: 0.21107125282287598 secondsTime to load utils op: 0.21107983589172363 seconds + 3: + 3: Time to load utils op: 0.21106982231140137 seconds + 3: Time to load utils op: 0.21107816696166992 seconds + 3: Time to load utils op: 0.21108555793762207 seconds + 3: Time to load utils op: 0.21109747886657715 seconds + 0: [2022-12-02 10:52:25,597] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 + 0: [2022-12-02 10:52:25,598] [INFO] [utils.py:828:see_memory_usage] MA 3.78 GB Max_MA 3.78 GB CA 3.9 GB Max_CA 4 GB + 0: [2022-12-02 10:52:25,598] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.19 GB, percent = 11.4% +41: Time to load utils op: 0.0010221004486083984 seconds +41: Time to load utils op: 0.0009634494781494141 seconds +41: Time to load utils op: 0.0013384819030761719 secondsTime to load utils op: 0.001338958740234375 seconds +41: +41: Time to load utils op: 0.0013394355773925781 seconds +41: Time to load utils op: 0.0013515949249267578 seconds +41: Time to load utils op: 0.0013766288757324219 seconds +41: Time to load utils op: 0.0013666152954101562 seconds +13: Time to load utils op: 0.0004620552062988281 seconds + 8: Time to load utils op: 0.0010447502136230469 seconds +13: Time to load utils op: 0.0004794597625732422 seconds +31: Time to load utils op: 0.0011970996856689453 secondsTime to load utils op: 0.0011963844299316406 seconds +31: +33: Time to load utils op: 0.0008203983306884766 seconds +13: Time to load utils op: 0.0004317760467529297 secondsTime to load utils op: 0.0004353523254394531 seconds +13: + 8: Time to load utils op: 0.0009927749633789062 seconds +13: Time to load utils op: 0.00040078163146972656 seconds +29: Time to load utils op: 0.0010464191436767578 seconds +31: Time to load utils op: 0.0012297630310058594 seconds + 8: Time to load utils op: 0.0012011528015136719 seconds +13: Time to load utils op: 0.0005357265472412109 seconds +13: Time to load utils op: 0.0005471706390380859 seconds +13: Time to load utils op: 0.0005092620849609375 seconds +29: Time to load utils op: 0.0013992786407470703 seconds +31: Time to load utils op: 0.0015132427215576172 secondsTime to load utils op: 0.0015392303466796875 secondsTime to load utils op: 0.0015227794647216797 seconds +31: +31: + 9: Time to load utils op: 0.0012631416320800781 seconds + 8: Time to load utils op: 0.0014989376068115234 seconds + 8: Time to load utils op: 0.0013763904571533203 seconds +31: Time to load utils op: 0.0015149116516113281 seconds + 8: Time to load utils op: 0.0013842582702636719 seconds + 9: Time to load utils op: 0.0013370513916015625 seconds + 8: Time to load utils op: 0.0013942718505859375 seconds +31: Time to load utils op: 0.001573324203491211 seconds + 8: Time to load utils op: 0.0014302730560302734 seconds +33: Time to load utils op: 0.0013973712921142578 seconds +29: Time to load utils op: 0.001520395278930664 seconds +29: Time to load utils op: 0.001573324203491211 seconds +29: Time to load utils op: 0.001474142074584961 seconds +29: Time to load utils op: 0.001561880111694336 seconds + 9: Time to load utils op: 0.0014910697937011719 seconds +29: Time to load utils op: 0.0015263557434082031 seconds +33: Time to load utils op: 0.0015149116516113281 seconds + 9: Time to load utils op: 0.0015213489532470703 secondsTime to load utils op: 0.0013687610626220703 seconds + 9: +29: Time to load utils op: 0.0016095638275146484 seconds +33: Time to load utils op: 0.0014889240264892578 secondsTime to load utils op: 0.001260995864868164 seconds +33: + 9: Time to load utils op: 0.0014691352844238281 seconds +33: Time to load utils op: 0.0013892650604248047 seconds + 9: Time to load utils op: 0.001377105712890625 seconds +33: Time to load utils op: 0.0015225410461425781 seconds + 9: Time to load utils op: 0.0015261173248291016 seconds +33: Time to load utils op: 0.0014684200286865234 seconds +43: Time to load utils op: 0.0005199909210205078 seconds +43: Time to load utils op: 0.0005095005035400391 seconds +43: Time to load utils op: 0.0005483627319335938 seconds +43: Time to load utils op: 0.000591278076171875 seconds +43: Time to load utils op: 0.0005548000335693359 secondsTime to load utils op: 0.0005478858947753906 seconds +43: +43: Time to load utils op: 0.0006365776062011719 seconds +43: Time to load utils op: 0.0006260871887207031 seconds +50: Time to load utils op: 0.0007903575897216797 seconds +50: Time to load utils op: 0.0012369155883789062 seconds +50: Time to load utils op: 0.0013017654418945312 seconds +50: Time to load utils op: 0.0013267993927001953 seconds +50: Time to load utils op: 0.0013704299926757812 seconds +50: Time to load utils op: 0.0013663768768310547 seconds +50: Time to load utils op: 0.0014216899871826172 seconds +50: Time to load utils op: 0.0014166831970214844 seconds +26: Time to load utils op: 0.0006062984466552734 seconds +32: Time to load utils op: 0.0004851818084716797 seconds +32: Time to load utils op: 0.0004813671112060547 seconds +32: Time to load utils op: 0.0004875659942626953 seconds +32: Time to load utils op: 0.00046753883361816406 secondsTime to load utils op: 0.00046181678771972656 secondsTime to load utils op: 0.0004711151123046875 seconds +32: +32: +32: Time to load utils op: 0.00045609474182128906 seconds +32: Time to load utils op: 0.0005323886871337891 seconds +58: Time to load utils op: 0.0005023479461669922 seconds +26: Time to load utils op: 0.0007975101470947266 seconds +58: Time to load utils op: 0.0005316734313964844 secondsTime to load utils op: 0.0005106925964355469 seconds +58: +58: Time to load utils op: 0.0005297660827636719 seconds +26: Time to load utils op: 0.0009562969207763672 seconds +26: Time to load utils op: 0.0009565353393554688 seconds +26: Time to load utils op: 0.0009570121765136719 seconds +58: Time to load utils op: 0.0005660057067871094 secondsTime to load utils op: 0.0005486011505126953 seconds +58: +58: Time to load utils op: 0.0005414485931396484 seconds +58: Time to load utils op: 0.0006213188171386719 seconds +26: Time to load utils op: 0.0010998249053955078 secondsTime to load utils op: 0.0010881423950195312 seconds +26: +26: Time to load utils op: 0.0011625289916992188 seconds +27: Time to load utils op: 0.0005891323089599609 seconds +27: Time to load utils op: 0.0005850791931152344 seconds +27: Time to load utils op: 0.0006029605865478516 seconds +27: Time to load utils op: 0.0006122589111328125 seconds +27: Time to load utils op: 0.0006232261657714844 seconds +27: Time to load utils op: 0.0006155967712402344 seconds +27: Time to load utils op: 0.0007023811340332031 seconds +27: Time to load utils op: 0.0006744861602783203 seconds +60: Time to load utils op: 0.0004928112030029297 seconds +60: Time to load utils op: 0.0005059242248535156 seconds +60: Time to load utils op: 0.0005247592926025391 seconds +60: Time to load utils op: 0.0004999637603759766 seconds +60: Time to load utils op: 0.0005650520324707031 seconds +60: Time to load utils op: 0.0005273818969726562 seconds +60: Time to load utils op: 0.0005595684051513672 seconds +60: Time to load utils op: 0.0006093978881835938 seconds +53: Time to load utils op: 0.00046062469482421875 seconds +53: Time to load utils op: 0.00040602684020996094 secondsTime to load utils op: 0.0004112720489501953 seconds +53: Time to load utils op: 0.0004367828369140625 seconds +53: +53: Time to load utils op: 0.0004127025604248047 seconds +53: Time to load utils op: 0.0005109310150146484 seconds +53: Time to load utils op: 0.0005002021789550781 seconds +53: Time to load utils op: 0.0005300045013427734 seconds + 7: Time to load utils op: 0.00043010711669921875 seconds + 7: Time to load utils op: 0.0004107952117919922 secondsTime to load utils op: 0.00040268898010253906 secondsTime to load utils op: 0.0003972053527832031 seconds + 7: + 7: + 7: Time to load utils op: 0.0004222393035888672 seconds + 7: Time to load utils op: 0.0004763603210449219 secondsTime to load utils op: 0.00047469139099121094 secondsTime to load utils op: 0.0004639625549316406 seconds + 7: + 7: +34: Time to load utils op: 0.0004558563232421875 seconds +34: Time to load utils op: 0.0004138946533203125 seconds +34: Time to load utils op: 0.000537872314453125 seconds +34: Time to load utils op: 0.0005340576171875 seconds +34: Time to load utils op: 0.0005552768707275391 seconds +34: Time to load utils op: 0.0005600452423095703 seconds +34: Time to load utils op: 0.0005605220794677734 seconds +34: Time to load utils op: 0.0006053447723388672 seconds +19: Time to load utils op: 0.0005159378051757812 secondsTime to load utils op: 0.0004925727844238281 seconds +19: +19: Time to load utils op: 0.0005090236663818359 seconds +19: Time to load utils op: 0.000553131103515625 seconds +11: Time to load utils op: 0.0008885860443115234 seconds +19: Time to load utils op: 0.0006251335144042969 seconds +19: Time to load utils op: 0.0006086826324462891 seconds +19: Time to load utils op: 0.0005545616149902344 seconds +19: Time to load utils op: 0.0005707740783691406 seconds +11: Time to load utils op: 0.0010638236999511719 seconds +38: Time to load utils op: 0.0010180473327636719 secondsTime to load utils op: 0.0010447502136230469 seconds +38: +11: Time to load utils op: 0.001148223876953125 seconds +11: Time to load utils op: 0.0013203620910644531 seconds +38: Time to load utils op: 0.0012717247009277344 seconds +38: Time to load utils op: 0.0012097358703613281 secondsTime to load utils op: 0.0012590885162353516 seconds +11: Time to load utils op: 0.0012180805206298828 seconds +38: Time to load utils op: 0.0012226104736328125 seconds +38: +11: Time to load utils op: 0.0013453960418701172 seconds +39: Time to load utils op: 0.0004820823669433594 seconds +11: Time to load utils op: 0.0012807846069335938 seconds +38: Time to load utils op: 0.0012187957763671875 seconds +39: Time to load utils op: 0.0004858970642089844 seconds +38: Time to load utils op: 0.001262664794921875 seconds +11: Time to load utils op: 0.0012793540954589844 seconds +39: Time to load utils op: 0.0006034374237060547 seconds +39: Time to load utils op: 0.0005993843078613281 seconds +39: Time to load utils op: 0.0005979537963867188 seconds +39: Time to load utils op: 0.0006661415100097656 seconds +39: Time to load utils op: 0.0006737709045410156 secondsTime to load utils op: 0.0007002353668212891 seconds +39: + 0: Time to load utils op: 0.0004878044128417969 seconds + 0: Time to load utils op: 0.0005230903625488281 seconds + 0: Time to load utils op: 0.00045990943908691406 secondsTime to load utils op: 0.00044417381286621094 secondsTime to load utils op: 0.0004680156707763672 seconds + 0: + 0: + 0: Time to load utils op: 0.00043892860412597656 seconds + 0: Time to load utils op: 0.0004971027374267578 seconds +54: Time to load utils op: 0.0008008480072021484 seconds +54: Time to load utils op: 0.0011763572692871094 seconds +54: Time to load utils op: 0.0013027191162109375 seconds +54: Time to load utils op: 0.0012612342834472656 seconds +54: Time to load utils op: 0.001279592514038086 seconds +54: Time to load utils op: 0.0013117790222167969 seconds +54: Time to load utils op: 0.0013222694396972656 seconds +54: Time to load utils op: 0.001336812973022461 seconds +63: Time to load utils op: 0.0005307197570800781 secondsTime to load utils op: 0.0005574226379394531 seconds +63: +63: Time to load utils op: 0.0005412101745605469 secondsTime to load utils op: 0.0005340576171875 seconds +63: +63: Time to load utils op: 0.0006337165832519531 seconds +63: Time to load utils op: 0.0006461143493652344 seconds +63: Time to load utils op: 0.0006651878356933594 seconds +63: Time to load utils op: 0.00030231475830078125 seconds +47: Time to load utils op: 0.0008244514465332031 seconds +36: Time to load utils op: 0.0010788440704345703 seconds +36: Time to load utils op: 0.0013289451599121094 seconds +17: Time to load utils op: 0.0008857250213623047 seconds +47: Time to load utils op: 0.0012581348419189453 secondsTime to load utils op: 0.0012965202331542969 seconds +47: +36: Time to load utils op: 0.0014684200286865234 seconds +36: Time to load utils op: 0.0014891624450683594 seconds +47: Time to load utils op: 0.0011975765228271484 secondsTime to load utils op: 0.0012712478637695312 seconds +47: +36: Time to load utils op: 0.0013980865478515625 seconds +47: Time to load utils op: 0.0012187957763671875 seconds +47: Time to load utils op: 0.0012469291687011719 seconds +36: Time to load utils op: 0.0014493465423583984 seconds +47: Time to load utils op: 0.0012786388397216797 seconds +36: Time to load utils op: 0.0014095306396484375 seconds +17: Time to load utils op: 0.001046895980834961 seconds +36: Time to load utils op: 0.0014841556549072266 seconds +17: Time to load utils op: 0.0012326240539550781 seconds +17: Time to load utils op: 0.0013365745544433594 seconds +17: Time to load utils op: 0.0012674331665039062 seconds +17: Time to load utils op: 0.001283407211303711 seconds +17: Time to load utils op: 0.0012545585632324219 seconds +45: Time to load utils op: 0.0008702278137207031 seconds +45: Time to load utils op: 0.0009098052978515625 seconds +17: Time to load utils op: 0.00139617919921875 seconds +48: Time to load utils op: 0.0004949569702148438 seconds +45: Time to load utils op: 0.0010685920715332031 seconds +48: Time to load utils op: 0.0005068778991699219 seconds +48: Time to load utils op: 0.0005393028259277344 seconds +45: Time to load utils op: 0.0010042190551757812 seconds +48: Time to load utils op: 0.0004646778106689453 seconds +48: Time to load utils op: 0.0004947185516357422 seconds +45: Time to load utils op: 0.001008749008178711 seconds +48: Time to load utils op: 0.0004911422729492188 secondsTime to load utils op: 0.00046324729919433594 seconds +48: +48: Time to load utils op: 0.00046563148498535156 seconds +45: Time to load utils op: 0.001026153564453125 seconds +45: Time to load utils op: 0.0010647773742675781 secondsTime to load utils op: 0.0010547637939453125 seconds +45: +57: Time to load utils op: 0.0009784698486328125 seconds +57: Time to load utils op: 0.0011551380157470703 seconds +57: Time to load utils op: 0.0011823177337646484 seconds +57: Time to load utils op: 0.00115966796875 seconds +57: Time to load utils op: 0.0011601448059082031 seconds +57: Time to load utils op: 0.001155853271484375 seconds +57: Time to load utils op: 0.0011408329010009766 seconds +57: Time to load utils op: 0.0011949539184570312 seconds +49: Time to load utils op: 0.0009596347808837891 seconds +49: Time to load utils op: 0.0009465217590332031 seconds +49: Time to load utils op: 0.0011281967163085938 seconds +49: Time to load utils op: 0.0013573169708251953 seconds +49: Time to load utils op: 0.0012657642364501953 secondsTime to load utils op: 0.0012896060943603516 seconds +49: +49: Time to load utils op: 0.0012593269348144531 seconds +49: Time to load utils op: 0.001377105712890625 seconds +30: Time to load utils op: 0.0009377002716064453 seconds +30: Time to load utils op: 0.0012197494506835938 seconds +30: Time to load utils op: 0.0012135505676269531 secondsTime to load utils op: 0.0011878013610839844 seconds +30: +30: Time to load utils op: 0.0012021064758300781 secondsTime to load utils op: 0.0011782646179199219 seconds +30: +30: Time to load utils op: 0.0011758804321289062 seconds +30: Time to load utils op: 0.00122833251953125 seconds + 2: Time to load utils op: 0.0010516643524169922 seconds + 2: Time to load utils op: 0.0011262893676757812 seconds + 2: Time to load utils op: 0.0010652542114257812 seconds + 2: Time to load utils op: 0.0011143684387207031 seconds + 2: Time to load utils op: 0.0012862682342529297 seconds + 2: Time to load utils op: 0.0012972354888916016 seconds + 2: Time to load utils op: 0.0012595653533935547 seconds + 2: Time to load utils op: 0.0012898445129394531 seconds + 3: Time to load utils op: 0.0009942054748535156 seconds + 3: Time to load utils op: 0.0009412765502929688 seconds + 3: Time to load utils op: 0.0011105537414550781 secondsTime to load utils op: 0.0010979175567626953 seconds + 3: + 3: Time to load utils op: 0.0011217594146728516 seconds + 3: Time to load utils op: 0.0011374950408935547 seconds + 3: Time to load utils op: 0.0011408329010009766 seconds + 3: Time to load utils op: 0.0011653900146484375 seconds +55: Time to load utils op: 0.0008432865142822266 seconds +55: Time to load utils op: 0.00077056884765625 seconds +55: Time to load utils op: 0.0009109973907470703 seconds + 1: Time to load utils op: 0.0009791851043701172 seconds + 1: Time to load utils op: 0.0010128021240234375 seconds +55: Time to load utils op: 0.0011181831359863281 seconds + 1: Time to load utils op: 0.0012049674987792969 seconds +55: Time to load utils op: 0.0012619495391845703 seconds + 1: Time to load utils op: 0.0013031959533691406 secondsTime to load utils op: 0.001322031021118164 seconds + 1: Time to load utils op: 0.00128173828125 seconds + 1: +55: Time to load utils op: 0.0013630390167236328 seconds + 1: Time to load utils op: 0.0012745857238769531 seconds +55: Time to load utils op: 0.0012900829315185547 seconds +55: Time to load utils op: 0.001360177993774414 seconds + 1: Time to load utils op: 0.0013713836669921875 seconds +59: Time to load utils op: 0.0008974075317382812 seconds +59: Time to load utils op: 0.0009737014770507812 secondsTime to load utils op: 0.0010197162628173828 seconds +59: +59: Time to load utils op: 0.0011107921600341797 seconds +59: Time to load utils op: 0.0010862350463867188 seconds +59: Time to load utils op: 0.0010938644409179688 seconds +59: Time to load utils op: 0.0011539459228515625 seconds +59: Time to load utils op: 0.001157999038696289 seconds +35: Time to load utils op: 0.0007174015045166016 seconds +35: Time to load utils op: 0.0009610652923583984 seconds +35: Time to load utils op: 0.0012707710266113281 seconds +35: Time to load utils op: 0.0011358261108398438 seconds +35: Time to load utils op: 0.0011496543884277344 seconds +35: Time to load utils op: 0.0012085437774658203 seconds +35: Time to load utils op: 0.0011723041534423828 seconds +35: Time to load utils op: 0.0012717247009277344 seconds + 0: [2022-12-02 10:52:25,792] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 0: [2022-12-02 10:52:25,792] [INFO] [utils.py:828:see_memory_usage] MA 7.73 GB Max_MA 7.73 GB CA 9.8 GB Max_CA 10 GB + 0: [2022-12-02 10:52:25,793] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.43 GB, percent = 11.4% +56: Time to load utils op: 0.0011959075927734375 seconds +56: Time to load utils op: 0.0014050006866455078 seconds +56: Time to load utils op: 0.0013773441314697266 seconds +56: Time to load utils op: 0.0013267993927001953 seconds +56: Time to load utils op: 0.0013720989227294922 seconds +56: Time to load utils op: 0.0013587474822998047 seconds +56: Time to load utils op: 0.0013456344604492188 seconds +56: Time to load utils op: 0.0013890266418457031 seconds +51: Time to load utils op: 0.0008652210235595703 seconds +51: Time to load utils op: 0.0008594989776611328 secondsTime to load utils op: 0.0008690357208251953 seconds +51: +51: Time to load utils op: 0.0012524127960205078 seconds +51: Time to load utils op: 0.0012657642364501953 seconds +51: Time to load utils op: 0.0011746883392333984 seconds +51: Time to load utils op: 0.0012664794921875 seconds +51: Time to load utils op: 0.0013110637664794922 seconds +37: Time to load utils op: 0.0011434555053710938 seconds +37: Time to load utils op: 0.0013477802276611328 secondsTime to load utils op: 0.001280069351196289 seconds +37: +37: Time to load utils op: 0.0012230873107910156 secondsTime to load utils op: 0.0012307167053222656 seconds +37: +37: Time to load utils op: 0.0012593269348144531 secondsTime to load utils op: 0.0012497901916503906 seconds +37: +37: Time to load utils op: 0.0013039112091064453 seconds + 0: [2022-12-02 10:52:25,843] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 + 0: [2022-12-02 10:52:25,844] [INFO] [utils.py:828:see_memory_usage] MA 7.73 GB Max_MA 7.73 GB CA 9.8 GB Max_CA 10 GB + 0: [2022-12-02 10:52:25,844] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.54 GB, percent = 11.4% + 6: Time to load utils op: 0.0005543231964111328 seconds + 6: Time to load utils op: 0.0005505084991455078 seconds + 6: Time to load utils op: 0.0005888938903808594 seconds + 6: Time to load utils op: 0.0005340576171875 seconds + 6: Time to load utils op: 0.0005688667297363281 seconds + 6: Time to load utils op: 0.0005621910095214844 seconds + 6: Time to load utils op: 0.0006377696990966797 seconds + 6: Time to load utils op: 0.0006318092346191406 seconds +14: Time to load utils op: 0.0012087821960449219 seconds +14: Time to load utils op: 0.0015289783477783203 seconds +14: Time to load utils op: 0.001519918441772461 seconds +14: Time to load utils op: 0.0015180110931396484 seconds +14: Time to load utils op: 0.0015468597412109375 seconds +14: Time to load utils op: 0.0015730857849121094 seconds +14: Time to load utils op: 0.0015425682067871094 seconds +14: Time to load utils op: 0.0016124248504638672 seconds + 0: [2022-12-02 10:52:25,905] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2022-12-02 10:52:25,905] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-02 10:52:25,906] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.76 GB, percent = 11.5% + 4: Time to load utils op: 0.0009429454803466797 seconds + 4: Time to load utils op: 0.0011508464813232422 seconds + 4: Time to load utils op: 0.0012178421020507812 secondsTime to load utils op: 0.0012214183807373047 seconds + 4: + 4: Time to load utils op: 0.0013048648834228516 seconds + 4: Time to load utils op: 0.0013003349304199219 seconds + 4: Time to load utils op: 0.0012671947479248047 seconds + 4: Time to load utils op: 0.0012826919555664062 seconds +61: Time to load utils op: 0.0005285739898681641 seconds +61: Time to load utils op: 0.0005617141723632812 seconds +61: Time to load utils op: 0.0005431175231933594 seconds +61: Time to load utils op: 0.0005838871002197266 secondsTime to load utils op: 0.0005726814270019531 seconds +61: +61: Time to load utils op: 0.000629425048828125 seconds +61: Time to load utils op: 0.0006144046783447266 seconds +61: Time to load utils op: 0.0006945133209228516 seconds + 5: Time to load utils op: 0.0011653900146484375 seconds + 5: Time to load utils op: 0.0012938976287841797 seconds + 5: Time to load utils op: 0.0013132095336914062 seconds + 5: Time to load utils op: 0.001323699951171875 seconds + 5: Time to load utils op: 0.001255035400390625 secondsTime to load utils op: 0.0012748241424560547 seconds + 5: + 5: Time to load utils op: 0.0012760162353515625 seconds + 5: Time to load utils op: 0.0013022422790527344 seconds +15: Time to load utils op: 0.0008282661437988281 seconds +15: Time to load utils op: 0.0012559890747070312 seconds +15: Time to load utils op: 0.0013041496276855469 seconds +15: Time to load utils op: 0.0011906623840332031 seconds +15: Time to load utils op: 0.0012042522430419922 seconds +15: Time to load utils op: 0.0012619495391845703 seconds +15: Time to load utils op: 0.0011734962463378906 seconds +15: Time to load utils op: 0.001291036605834961 seconds +25: Time to load utils op: 0.0006005764007568359 seconds +25: Time to load utils op: 0.0008935928344726562 seconds +25: Time to load utils op: 0.0011920928955078125 seconds +25: Time to load utils op: 0.0011794567108154297 seconds +25: Time to load utils op: 0.0011379718780517578 seconds +25: Time to load utils op: 0.001188039779663086 seconds +25: Time to load utils op: 0.0011987686157226562 seconds +25: Time to load utils op: 0.0012888908386230469 seconds + 0: [2022-12-02 10:52:25,955] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: [2022-12-02 10:52:25,955] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-02 10:52:25,955] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.89 GB, percent = 11.5% +42: Time to load utils op: 0.0008928775787353516 seconds +42: Time to load utils op: 0.001130819320678711 seconds +42: Time to load utils op: 0.0011801719665527344 seconds +42: Time to load utils op: 0.0012722015380859375 seconds +42: Time to load utils op: 0.0013082027435302734 seconds +42: Time to load utils op: 0.0012903213500976562 secondsTime to load utils op: 0.001306295394897461 seconds +42: +42: Time to load utils op: 0.0013577938079833984 seconds +20: Time to load utils op: 0.0009286403656005859 seconds +20: Time to load utils op: 0.0009937286376953125 seconds +20: Time to load utils op: 0.001237630844116211 seconds +20: Time to load utils op: 0.0013730525970458984 seconds +20: Time to load utils op: 0.0012943744659423828 seconds +20: Time to load utils op: 0.0012404918670654297 seconds +20: Time to load utils op: 0.0013065338134765625 seconds +20: Time to load utils op: 0.0013759136199951172 seconds +23: Time to load utils op: 0.0009396076202392578 seconds +23: Time to load utils op: 0.0010576248168945312 seconds +23: Time to load utils op: 0.0012722015380859375 seconds +23: Time to load utils op: 0.0011279582977294922 seconds +23: Time to load utils op: 0.0011849403381347656 seconds +23: Time to load utils op: 0.0011794567108154297 seconds +23: Time to load utils op: 0.001188516616821289 seconds +23: Time to load utils op: 0.001220703125 seconds +12: Time to load utils op: 0.0006778240203857422 seconds +12: Time to load utils op: 0.001028299331665039 seconds +12: Time to load utils op: 0.0010209083557128906 seconds +12: Time to load utils op: 0.0011935234069824219 secondsTime to load utils op: 0.001247406005859375 seconds +12: +12: Time to load utils op: 0.0012328624725341797 seconds +12: Time to load utils op: 0.0012118816375732422 seconds +12: Time to load utils op: 0.0013234615325927734 seconds + 0: [2022-12-02 10:52:25,998] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 0: [2022-12-02 10:52:25,999] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-02 10:52:25,999] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.9 GB, percent = 11.5% +24: Time to load utils op: 0.0011687278747558594 seconds +24: Time to load utils op: 0.0011906623840332031 seconds +24: Time to load utils op: 0.0012645721435546875 seconds +24: Time to load utils op: 0.0012955665588378906 seconds +24: Time to load utils op: 0.0013957023620605469 seconds +24: Time to load utils op: 0.001310110092163086 seconds +24: Time to load utils op: 0.0012853145599365234 seconds +24: Time to load utils op: 0.0013456344604492188 seconds + 0: [2022-12-02 10:52:26,031] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 0: [2022-12-02 10:52:26,032] [INFO] [utils.py:828:see_memory_usage] MA 11.36 GB Max_MA 11.36 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-02 10:52:26,032] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.9 GB, percent = 11.5% +22: Time to load utils op: 0.0007476806640625 seconds +22: Time to load utils op: 0.0012884140014648438 seconds +22: Time to load utils op: 0.0012125968933105469 seconds +22: Time to load utils op: 0.0012311935424804688 seconds +22: Time to load utils op: 0.0012793540954589844 seconds +22: Time to load utils op: 0.001270294189453125 seconds +22: Time to load utils op: 0.0012123584747314453 seconds +22: Time to load utils op: 0.001318216323852539 seconds +52: Time to load utils op: 0.0005424022674560547 seconds +52: Time to load utils op: 0.0005359649658203125 seconds +52: Time to load utils op: 0.0005884170532226562 seconds +52: Time to load utils op: 0.0005669593811035156 secondsTime to load utils op: 0.0005638599395751953 seconds +52: +52: Time to load utils op: 0.0005991458892822266 seconds +52: Time to load utils op: 0.0005946159362792969 seconds +52: Time to load utils op: 0.0005679130554199219 seconds +21: Time to load utils op: 0.0008680820465087891 seconds +21: Time to load utils op: 0.001178741455078125 seconds +21: Time to load utils op: 0.0011630058288574219 seconds +21: Time to load utils op: 0.0011851787567138672 secondsTime to load utils op: 0.0011501312255859375 seconds +21: +21: Time to load utils op: 0.0011463165283203125 seconds +21: Time to load utils op: 0.0011589527130126953 seconds +21: Time to load utils op: 0.0012192726135253906 seconds +44: Time to load utils op: 0.0005035400390625 seconds +44: Time to load utils op: 0.0004246234893798828 seconds +44: Time to load utils op: 0.0005719661712646484 secondsTime to load utils op: 0.0005881786346435547 seconds +44: Time to load utils op: 0.0005967617034912109 seconds +44: +44: Time to load utils op: 0.0005712509155273438 seconds +44: Time to load utils op: 0.0006279945373535156 seconds +44: Time to load utils op: 0.0006568431854248047 seconds +28: Time to load utils op: 0.0010499954223632812 seconds +28: Time to load utils op: 0.001322031021118164 seconds +28: Time to load utils op: 0.001313924789428711 seconds +28: Time to load utils op: 0.0012319087982177734 seconds +28: Time to load utils op: 0.0012509822845458984 secondsTime to load utils op: 0.0012431144714355469 seconds +28: Time to load utils op: 0.0012607574462890625 seconds +28: +28: Time to load utils op: 0.0012805461883544922 seconds +16: Time to load utils op: 0.0005428791046142578 seconds +16: Time to load utils op: 0.0005726814270019531 seconds +16: Time to load utils op: 0.0005581378936767578 seconds +16: Time to load utils op: 0.0005729198455810547 secondsTime to load utils op: 0.0005898475646972656 seconds +16: +16: Time to load utils op: 0.0006186962127685547 seconds +16: Time to load utils op: 0.0005757808685302734 seconds +18: Time to load utils op: 0.0009350776672363281 seconds +16: Time to load utils op: 0.0006592273712158203 seconds +18: Time to load utils op: 0.0010700225830078125 seconds +10: Time to load utils op: 0.0008282661437988281 seconds +62: Time to load utils op: 0.0005412101745605469 seconds +40: Time to load utils op: 0.0014584064483642578 seconds +40: Time to load utils op: 0.0013670921325683594 secondsTime to load utils op: 0.0014452934265136719 seconds +40: +40: Time to load utils op: 0.0014989376068115234 seconds +62: Time to load utils op: 0.0005540847778320312 seconds +62: Time to load utils op: 0.00054168701171875 seconds +40: Time to load utils op: 0.0015342235565185547 seconds +10: Time to load utils op: 0.0008199214935302734 secondsTime to load utils op: 0.0008878707885742188 seconds +10: +40: Time to load utils op: 0.0015027523040771484 seconds +40: Time to load utils op: 0.0014281272888183594 seconds +40: Time to load utils op: 0.0015101432800292969 seconds +62: Time to load utils op: 0.0005803108215332031 seconds +62: Time to load utils op: 0.0006034374237060547 seconds +62: Time to load utils op: 0.0006248950958251953 secondsTime to load utils op: 0.00064849853515625 seconds +62: +62: Time to load utils op: 0.0005860328674316406 seconds +18: Time to load utils op: 0.0012888908386230469 seconds +10: Time to load utils op: 0.0011610984802246094 seconds +18: Time to load utils op: 0.0012912750244140625 seconds +10: Time to load utils op: 0.0011663436889648438 secondsTime to load utils op: 0.0011515617370605469 seconds +10: +18: Time to load utils op: 0.0012660026550292969 seconds +10: Time to load utils op: 0.00118255615234375 seconds +18: Time to load utils op: 0.0013070106506347656 seconds +18: Time to load utils op: 0.0012629032135009766 seconds +10: Time to load utils op: 0.0012097358703613281 seconds +18: Time to load utils op: 0.0012974739074707031 seconds +46: Time to load utils op: 0.0009064674377441406 seconds +46: Time to load utils op: 0.0011131763458251953 seconds +46: Time to load utils op: 0.0013773441314697266 seconds +46: Time to load utils op: 0.001401662826538086 secondsTime to load utils op: 0.0013568401336669922 seconds +46: +46: Time to load utils op: 0.0012729167938232422 seconds +46: Time to load utils op: 0.0012619495391845703 seconds +46: Time to load utils op: 0.0013439655303955078 seconds + 0: [2022-12-02 10:52:26,069] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer + 0: [2022-12-02 10:52:26,069] [INFO] [utils.py:828:see_memory_usage] MA 11.42 GB Max_MA 11.42 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-02 10:52:26,069] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.9 GB, percent = 11.5% + 0: [2022-12-02 10:52:26,101] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2022-12-02 10:52:26,102] [INFO] [utils.py:828:see_memory_usage] MA 11.42 GB Max_MA 11.42 GB CA 15.23 GB Max_CA 15 GB + 0: [2022-12-02 10:52:26,102] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 57.9 GB, percent = 11.5% + 0: [2022-12-02 10:52:26,102] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2022-12-02 10:52:26,102] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2022-12-02 10:52:26,102] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2022-12-02 10:52:26,102] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] activation_checkpointing_config { + 0: "partition_activations": false, + 0: "contiguous_memory_optimization": false, + 0: "cpu_checkpointing": false, + 0: "number_checkpoints": null, + 0: "synchronize_checkpoint_boundary": false, + 0: "profile": false + 0: } + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] autotuning_config ............ { + 0: "enabled": false, + 0: "start_step": null, + 0: "end_step": null, + 0: "metric_path": null, + 0: "arg_mappings": null, + 0: "metric": "throughput", + 0: "model_info": null, + 0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", + 0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", + 0: "overwrite": true, + 0: "fast": true, + 0: "start_profile_step": 3, + 0: "end_profile_step": 5, + 0: "tuner_type": "gridsearch", + 0: "tuner_early_stopping": 5, + 0: "tuner_num_trials": 50, + 0: "model_info_path": null, + 0: "mp_size": 1, + 0: "max_train_batch_size": null, + 0: "min_train_batch_size": 1, + 0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, + 0: "min_train_micro_batch_size_per_gpu": 1, + 0: "num_tuning_micro_batch_sizes": 3 + 0: } + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] comms_config ................. + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa + 0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2022-12-02 10:52:26,103] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] flops_profiler_config ........ { + 0: "enabled": false, + 0: "profile_step": 1, + 0: "module_depth": -1, + 0: "top_modules": 1, + 0: "detailed": true, + 0: "output_file": null + 0: } + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 2 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] nebula_config ................ { + 0: "enabled": false, + 0: "persistent_storage_path": null, + 0: "persistent_time_interval": 100, + 0: "num_of_version_in_retention": 2, + 0: "enable_nebula_load": true, + 0: "load_path": null + 0: } + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] train_batch_size ............. 512 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2022-12-02 10:52:26,104] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:1011:print] world_size ................... 256 + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2022-12-02 10:52:26,105] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 0: "train_batch_size": 512, + 0: "gradient_clipping": 1.0, + 0: "zero_optimization": { + 0: "stage": 0 + 0: }, + 0: "bf16": { + 0: "enabled": true + 0: }, + 0: "steps_per_print": 2.000000e+03, + 0: "wall_clock_breakdown": false + 0: } + 0: Time to load utils op: 0.00040030479431152344 seconds + 0: [2022-12-02 10:52:26,105] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=2 micro_batch_size=1 + 0: [2022-12-02 10:52:26,347] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=21 [0, 21) STAGE_PARAMS=2026914560 (2026.915M) TOTAL_PARAMS=4053835008 (4053.835M) UNIQUE_PARAMS=3899710720 (3899.711M) +32: [2022-12-02 10:52:26,347] [INFO] [engine.py:145:__init__] RANK=256 STAGE=1 LAYERS=22 [21, 43) STAGE_PARAMS=2026920448 (2026.920M) TOTAL_PARAMS=4053835008 (4053.835M) UNIQUE_PARAMS=3899710720 (3899.711M) + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +56: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +60: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +48: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +62: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +45: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +52: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +54: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +55: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +53: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +35: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +57: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +58: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +39: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +61: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +47: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +46: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 0: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 0: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +62: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +48: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +37: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +48: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +12: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +59: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +32: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +12: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +20: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +52: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +54: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +60: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +12: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +11: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +63: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 0: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +46: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +20: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 9: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +28: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +56: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +19: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +20: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +58: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +12: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 9: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +55: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +29: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +20: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 6: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 6: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +45: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +47: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +23: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +25: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 1: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +50: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +38: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +41: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +43: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 2: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +10: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +34: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +31: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +42: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +10: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +35: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +23: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +39: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +21: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +23: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +21: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +14: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 1: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +49: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 2: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +15: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +31: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +57: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +31: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +44: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +49: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +15: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +24: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +53: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 8: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +22: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +13: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 4: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt... +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +51: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +61: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 7: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +26: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +13: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +40: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +18: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +26: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +33: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +36: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt... +17: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +18: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +13: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +26: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_00_model_states.pt. + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:28,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:28,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +45: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +48: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +54: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +62: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +60: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +53: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +56: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +32: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +35: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +46: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +40: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +63: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +47: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +38: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +44: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +42: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +41: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +33: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +59: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +58: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +51: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +61: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +49: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +39: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +57: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +36: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +55: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +34: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +43: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +37: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/mp_rank_01_model_states.pt. +50: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:28,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:28,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +41: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +62: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +48: [2022-12-02 10:52:29,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +41: [2022-12-02 10:52:29,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +62: [2022-12-02 10:52:29,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:29,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:29,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:29,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +48: [2022-12-02 10:52:29,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:29,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:29,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:29,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:29,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:29,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +35: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:29,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:29,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:29,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +56: [2022-12-02 10:52:29,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:29,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:29,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:29,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +51: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +33: [2022-12-02 10:52:29,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +49: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:29,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +45: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +53: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +55: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +53: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +59: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +44: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +57: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +39: [2022-12-02 10:52:29,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +52: [2022-12-02 10:52:29,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +61: [2022-12-02 10:52:29,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +63: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +49: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +60: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +50: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +34: [2022-12-02 10:52:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +47: [2022-12-02 10:52:29,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +50: [2022-12-02 10:52:29,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +43: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +61: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +61: [2022-12-02 10:52:29,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +54: [2022-12-02 10:52:29,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +43: [2022-12-02 10:52:29,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:29,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:29,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +47: [2022-12-02 10:52:29,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +42: [2022-12-02 10:52:29,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:29,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:29,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +42: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +43: [2022-12-02 10:52:29,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +45: [2022-12-02 10:52:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +11: [2022-12-02 10:52:29,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +33: [2022-12-02 10:52:29,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +11: [2022-12-02 10:52:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +39: [2022-12-02 10:52:29,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +11: [2022-12-02 10:52:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +63: [2022-12-02 10:52:29,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +32: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +45: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +17: [2022-12-02 10:52:29,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +59: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +37: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:29,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +58: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +58: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +37: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +36: [2022-12-02 10:52:29,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +36: [2022-12-02 10:52:29,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:29,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:29,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +35: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:29,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:29,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +17: [2022-12-02 10:52:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +33: [2022-12-02 10:52:29,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +17: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +17: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +40: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +17: [2022-12-02 10:52:29,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +56: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +17: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +47: [2022-12-02 10:52:29,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +45: [2022-12-02 10:52:29,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +33: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +52: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +52: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +56: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +45: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +45: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +46: [2022-12-02 10:52:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:29,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:29,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +38: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +39: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +51: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +34: [2022-12-02 10:52:29,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +52: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +32: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +40: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt... +38: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +32: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +46: [2022-12-02 10:52:29,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +33: [2022-12-02 10:52:29,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:29,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:29,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:29,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:29,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:29,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:29,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:29,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +57: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +52: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +46: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +46: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +59: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +55: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +60: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:29,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +21: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +61: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +59: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +21: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +52: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +21: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +61: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +21: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +46: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +46: [2022-12-02 10:52:29,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +57: [2022-12-02 10:52:29,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +47: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +31: [2022-12-02 10:52:29,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +60: [2022-12-02 10:52:29,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +61: [2022-12-02 10:52:29,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +63: [2022-12-02 10:52:29,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +44: [2022-12-02 10:52:29,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:29,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +47: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:29,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +45: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +29: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +45: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:29,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:29,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:29,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:29,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +30: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +39: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +21: [2022-12-02 10:52:29,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +21: [2022-12-02 10:52:29,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +44: [2022-12-02 10:52:29,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +32: [2022-12-02 10:52:29,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +31: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +52: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +32: [2022-12-02 10:52:29,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +34: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +31: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +34: [2022-12-02 10:52:29,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:29,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +29: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +54: [2022-12-02 10:52:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +30: [2022-12-02 10:52:29,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +54: [2022-12-02 10:52:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +30: [2022-12-02 10:52:29,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +54: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +46: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +28: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +37: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +54: [2022-12-02 10:52:29,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +46: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +14: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +37: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +22: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +61: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +22: [2022-12-02 10:52:29,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +47: [2022-12-02 10:52:29,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:29,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +61: [2022-12-02 10:52:29,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +20: [2022-12-02 10:52:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +46: [2022-12-02 10:52:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +47: [2022-12-02 10:52:29,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +20: [2022-12-02 10:52:29,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +37: [2022-12-02 10:52:29,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +28: [2022-12-02 10:52:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +61: [2022-12-02 10:52:29,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:29,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:29,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +20: [2022-12-02 10:52:29,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:29,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:29,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:29,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:29,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +61: [2022-12-02 10:52:29,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +18: [2022-12-02 10:52:29,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +40: [2022-12-02 10:52:29,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +18: [2022-12-02 10:52:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +40: [2022-12-02 10:52:29,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +11: [2022-12-02 10:52:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +40: [2022-12-02 10:52:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +40: [2022-12-02 10:52:29,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_21-model_00-model_states.pt. +37: [2022-12-02 10:52:29,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +37: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +37: [2022-12-02 10:52:29,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:29,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +37: [2022-12-02 10:52:29,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:29,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +17: [2022-12-02 10:52:29,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:29,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 8: [2022-12-02 10:52:29,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:29,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:29,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:29,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:29,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:29,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +40: [2022-12-02 10:52:29,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +17: [2022-12-02 10:52:29,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +40: [2022-12-02 10:52:29,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +23: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +40: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +23: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:29,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +40: [2022-12-02 10:52:29,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +11: [2022-12-02 10:52:29,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:29,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:29,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +40: [2022-12-02 10:52:29,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:29,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +40: [2022-12-02 10:52:29,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +15: [2022-12-02 10:52:29,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +11: [2022-12-02 10:52:29,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:29,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +11: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:29,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:29,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +17: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +15: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +17: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:29,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +20: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +27: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +25: [2022-12-02 10:52:29,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +16: [2022-12-02 10:52:29,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +29: [2022-12-02 10:52:29,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +19: [2022-12-02 10:52:29,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:29,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:29,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:29,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:29,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +10: [2022-12-02 10:52:29,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 9: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +21: [2022-12-02 10:52:29,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 0: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +18: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +31: [2022-12-02 10:52:29,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:29,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:29,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:29,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:29,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:29,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:29,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:29,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +24: [2022-12-02 10:52:29,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +31: [2022-12-02 10:52:29,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:29,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:29,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:29,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:29,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:29,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 7: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +23: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +22: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +13: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +22: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:29,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:29,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +12: [2022-12-02 10:52:29,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +12: [2022-12-02 10:52:29,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +12: [2022-12-02 10:52:29,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +14: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +12: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +29: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +14: [2022-12-02 10:52:29,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:29,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +30: [2022-12-02 10:52:29,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +30: [2022-12-02 10:52:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:29,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:29,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:29,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:29,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:29,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +26: [2022-12-02 10:52:29,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:29,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:29,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:29,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +18: [2022-12-02 10:52:29,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt... +28: [2022-12-02 10:52:29,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:29,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:29,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +20: [2022-12-02 10:52:29,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:29,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:29,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:29,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:29,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +23: [2022-12-02 10:52:29,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +28: [2022-12-02 10:52:29,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:29,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 1: [2022-12-02 10:52:29,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 2: [2022-12-02 10:52:29,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:29,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 5: [2022-12-02 10:52:29,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:29,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:29,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +15: [2022-12-02 10:52:29,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:29,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +16: [2022-12-02 10:52:29,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:29,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:29,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:29,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +25: [2022-12-02 10:52:29,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +10: [2022-12-02 10:52:29,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:29,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:29,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 4: [2022-12-02 10:52:29,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +24: [2022-12-02 10:52:29,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 6: [2022-12-02 10:52:29,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:29,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +19: [2022-12-02 10:52:29,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +27: [2022-12-02 10:52:29,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:29,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:29,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +41: [2022-12-02 10:52:29,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +10: [2022-12-02 10:52:29,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:29,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +13: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +10: [2022-12-02 10:52:29,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:29,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +12: [2022-12-02 10:52:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:29,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +12: [2022-12-02 10:52:29,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:29,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +24: [2022-12-02 10:52:29,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +24: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +43: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:29,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +13: [2022-12-02 10:52:29,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:29,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +43: [2022-12-02 10:52:29,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:29,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +43: [2022-12-02 10:52:29,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:29,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +26: [2022-12-02 10:52:29,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_01-model_00-model_states.pt. +13: [2022-12-02 10:52:29,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:29,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +49: [2022-12-02 10:52:29,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:29,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +49: [2022-12-02 10:52:29,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:29,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +48: [2022-12-02 10:52:29,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 3: [2022-12-02 10:52:29,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +48: [2022-12-02 10:52:29,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 3: [2022-12-02 10:52:29,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:29,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +48: [2022-12-02 10:52:29,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +41: [2022-12-02 10:52:29,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +41: [2022-12-02 10:52:29,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:29,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +43: [2022-12-02 10:52:30,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:30,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:30,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +43: [2022-12-02 10:52:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +62: [2022-12-02 10:52:30,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:30,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:30,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:30,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +49: [2022-12-02 10:52:30,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +62: [2022-12-02 10:52:30,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +49: [2022-12-02 10:52:30,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +48: [2022-12-02 10:52:30,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +35: [2022-12-02 10:52:30,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +42: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +50: [2022-12-02 10:52:30,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +35: [2022-12-02 10:52:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +50: [2022-12-02 10:52:30,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +42: [2022-12-02 10:52:30,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +51: [2022-12-02 10:52:30,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +51: [2022-12-02 10:52:30,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:30,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +38: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +34: [2022-12-02 10:52:30,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +58: [2022-12-02 10:52:30,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +17: [2022-12-02 10:52:30,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +36: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +17: [2022-12-02 10:52:30,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +56: [2022-12-02 10:52:30,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +56: [2022-12-02 10:52:30,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:30,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +54: [2022-12-02 10:52:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +61: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +17: [2022-12-02 10:52:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:30,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +54: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +59: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +11: [2022-12-02 10:52:30,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +46: [2022-12-02 10:52:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +61: [2022-12-02 10:52:30,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +52: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:30,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +46: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +54: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +57: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +11: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +52: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +52: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +55: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +32: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +14: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +37: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +14: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +58: [2022-12-02 10:52:30,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +14: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +32: [2022-12-02 10:52:30,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:30,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +59: [2022-12-02 10:52:30,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +39: [2022-12-02 10:52:30,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +37: [2022-12-02 10:52:30,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +58: [2022-12-02 10:52:30,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +14: [2022-12-02 10:52:30,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +60: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +59: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +59: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +32: [2022-12-02 10:52:30,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +14: [2022-12-02 10:52:30,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +60: [2022-12-02 10:52:30,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +14: [2022-12-02 10:52:30,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +33: [2022-12-02 10:52:30,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +14: [2022-12-02 10:52:30,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:30,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:30,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:30,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:30,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +56: [2022-12-02 10:52:30,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:30,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +33: [2022-12-02 10:52:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:30,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +60: [2022-12-02 10:52:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +36: [2022-12-02 10:52:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +56: [2022-12-02 10:52:30,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +33: [2022-12-02 10:52:30,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +45: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +36: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +33: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +56: [2022-12-02 10:52:30,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +53: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +63: [2022-12-02 10:52:30,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +40: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +47: [2022-12-02 10:52:30,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +45: [2022-12-02 10:52:30,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +63: [2022-12-02 10:52:30,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:30,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:30,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +44: [2022-12-02 10:52:30,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:30,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +63: [2022-12-02 10:52:30,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +47: [2022-12-02 10:52:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:30,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +47: [2022-12-02 10:52:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt... +53: [2022-12-02 10:52:30,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +17: [2022-12-02 10:52:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +38: [2022-12-02 10:52:30,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +53: [2022-12-02 10:52:30,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +39: [2022-12-02 10:52:30,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +39: [2022-12-02 10:52:30,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +31: [2022-12-02 10:52:30,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +54: [2022-12-02 10:52:30,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +31: [2022-12-02 10:52:30,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +37: [2022-12-02 10:52:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +14: [2022-12-02 10:52:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +40: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +57: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +34: [2022-12-02 10:52:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +11: [2022-12-02 10:52:30,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +34: [2022-12-02 10:52:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +38: [2022-12-02 10:52:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +11: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +54: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +30: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +54: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +37: [2022-12-02 10:52:30,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +30: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +55: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +40: [2022-12-02 10:52:30,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +46: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +46: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +30: [2022-12-02 10:52:30,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +11: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +39: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +11: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +39: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +39: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +39: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +60: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +14: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +61: [2022-12-02 10:52:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +30: [2022-12-02 10:52:30,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +17: [2022-12-02 10:52:30,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +46: [2022-12-02 10:52:30,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +29: [2022-12-02 10:52:30,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +46: [2022-12-02 10:52:30,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +17: [2022-12-02 10:52:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +39: [2022-12-02 10:52:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +54: [2022-12-02 10:52:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +52: [2022-12-02 10:52:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +52: [2022-12-02 10:52:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +17: [2022-12-02 10:52:30,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +47: [2022-12-02 10:52:30,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +17: [2022-12-02 10:52:30,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +54: [2022-12-02 10:52:30,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +37: [2022-12-02 10:52:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +17: [2022-12-02 10:52:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +37: [2022-12-02 10:52:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +57: [2022-12-02 10:52:30,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +55: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +20: [2022-12-02 10:52:30,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +57: [2022-12-02 10:52:30,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +37: [2022-12-02 10:52:30,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +20: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +57: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +14: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +57: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +20: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +63: [2022-12-02 10:52:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +20: [2022-12-02 10:52:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +14: [2022-12-02 10:52:30,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +54: [2022-12-02 10:52:30,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +57: [2022-12-02 10:52:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +60: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +57: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +54: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +37: [2022-12-02 10:52:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +20: [2022-12-02 10:52:30,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +52: [2022-12-02 10:52:30,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +20: [2022-12-02 10:52:30,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +55: [2022-12-02 10:52:30,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +63: [2022-12-02 10:52:30,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +63: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +54: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +55: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +39: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +61: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +52: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +39: [2022-12-02 10:52:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +20: [2022-12-02 10:52:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:30,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +11: [2022-12-02 10:52:30,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +46: [2022-12-02 10:52:30,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +46: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +14: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +11: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +46: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +44: [2022-12-02 10:52:30,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +39: [2022-12-02 10:52:30,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +14: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +63: [2022-12-02 10:52:30,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +44: [2022-12-02 10:52:30,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +23: [2022-12-02 10:52:30,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +61: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +47: [2022-12-02 10:52:30,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +44: [2022-12-02 10:52:30,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +47: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +47: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +60: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +60: [2022-12-02 10:52:30,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +44: [2022-12-02 10:52:30,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +47: [2022-12-02 10:52:30,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_22-model_00-model_states.pt. +61: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +31: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +47: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:30,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +63: [2022-12-02 10:52:30,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +16: [2022-12-02 10:52:30,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +30: [2022-12-02 10:52:30,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +63: [2022-12-02 10:52:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +63: [2022-12-02 10:52:30,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +63: [2022-12-02 10:52:30,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +31: [2022-12-02 10:52:30,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:30,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +47: [2022-12-02 10:52:30,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +47: [2022-12-02 10:52:30,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +30: [2022-12-02 10:52:30,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +47: [2022-12-02 10:52:30,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +47: [2022-12-02 10:52:30,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +30: [2022-12-02 10:52:30,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +47: [2022-12-02 10:52:30,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 0: [2022-12-02 10:52:30,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:30,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:30,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +31: [2022-12-02 10:52:30,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:30,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:30,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +29: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +20: [2022-12-02 10:52:30,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +29: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 6: [2022-12-02 10:52:30,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:30,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:30,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:30,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:30,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +30: [2022-12-02 10:52:30,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:30,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:30,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:30,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 8: [2022-12-02 10:52:30,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:30,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:30,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:30,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:30,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 7: [2022-12-02 10:52:30,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +23: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +20: [2022-12-02 10:52:30,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +23: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:30,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:30,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +25: [2022-12-02 10:52:30,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:30,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +41: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +41: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:30,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:30,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:30,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:30,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +16: [2022-12-02 10:52:30,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:30,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +41: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +10: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +41: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:30,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +10: [2022-12-02 10:52:30,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:30,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:30,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +10: [2022-12-02 10:52:30,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:30,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:30,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:30,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:30,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:30,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +21: [2022-12-02 10:52:30,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +21: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +15: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +12: [2022-12-02 10:52:30,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +16: [2022-12-02 10:52:30,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:30,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:30,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:30,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +28: [2022-12-02 10:52:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:30,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 9: [2022-12-02 10:52:30,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 9: [2022-12-02 10:52:30,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:30,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:30,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +18: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +13: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:30,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:30,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +26: [2022-12-02 10:52:30,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +22: [2022-12-02 10:52:30,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +19: [2022-12-02 10:52:30,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +15: [2022-12-02 10:52:30,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:30,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:30,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:30,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +22: [2022-12-02 10:52:30,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +25: [2022-12-02 10:52:30,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +18: [2022-12-02 10:52:30,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:30,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:30,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:30,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +19: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +19: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +24: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +48: [2022-12-02 10:52:30,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +27: [2022-12-02 10:52:30,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +27: [2022-12-02 10:52:30,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +24: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +10: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +41: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +41: [2022-12-02 10:52:30,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +10: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +48: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +48: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +12: [2022-12-02 10:52:30,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +28: [2022-12-02 10:52:30,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +27: [2022-12-02 10:52:30,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +48: [2022-12-02 10:52:30,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +48: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +27: [2022-12-02 10:52:30,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +12: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +43: [2022-12-02 10:52:30,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +19: [2022-12-02 10:52:30,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +43: [2022-12-02 10:52:30,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +13: [2022-12-02 10:52:30,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:30,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +50: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +26: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +19: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +50: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +24: [2022-12-02 10:52:30,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +50: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +25: [2022-12-02 10:52:30,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +35: [2022-12-02 10:52:30,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +25: [2022-12-02 10:52:30,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:30,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:30,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +26: [2022-12-02 10:52:30,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +41: [2022-12-02 10:52:30,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +35: [2022-12-02 10:52:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +35: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt... +50: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +24: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +10: [2022-12-02 10:52:30,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:30,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +35: [2022-12-02 10:52:30,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +50: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +10: [2022-12-02 10:52:30,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +32: [2022-12-02 10:52:30,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +24: [2022-12-02 10:52:30,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:30,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +13: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +32: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +24: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +32: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +26: [2022-12-02 10:52:30,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +24: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +32: [2022-12-02 10:52:30,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +41: [2022-12-02 10:52:30,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:30,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +10: [2022-12-02 10:52:30,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:30,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +32: [2022-12-02 10:52:30,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +10: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +10: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +56: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +12: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:30,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:30,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +27: [2022-12-02 10:52:30,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +56: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 5: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +32: [2022-12-02 10:52:30,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 5: [2022-12-02 10:52:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +56: [2022-12-02 10:52:30,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +27: [2022-12-02 10:52:30,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +13: [2022-12-02 10:52:30,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +26: [2022-12-02 10:52:30,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +62: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +62: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +53: [2022-12-02 10:52:30,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +26: [2022-12-02 10:52:30,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +53: [2022-12-02 10:52:30,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +48: [2022-12-02 10:52:30,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 1: [2022-12-02 10:52:30,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 4: [2022-12-02 10:52:30,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +28: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +43: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +13: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +43: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +26: [2022-12-02 10:52:30,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:30,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +48: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +13: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +49: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +13: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:30,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:30,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:30,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:30,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +48: [2022-12-02 10:52:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +42: [2022-12-02 10:52:30,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +35: [2022-12-02 10:52:30,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +42: [2022-12-02 10:52:30,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 2: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +42: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +35: [2022-12-02 10:52:30,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:30,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:30,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +51: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_03-model_00-model_states.pt. +44: [2022-12-02 10:52:30,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +48: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +43: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +35: [2022-12-02 10:52:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +48: [2022-12-02 10:52:30,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +44: [2022-12-02 10:52:30,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +44: [2022-12-02 10:52:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +51: [2022-12-02 10:52:30,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:30,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:30,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:30,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 2: [2022-12-02 10:52:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +44: [2022-12-02 10:52:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +44: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +43: [2022-12-02 10:52:30,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:30,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:30,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:30,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:30,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +50: [2022-12-02 10:52:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:30,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:30,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:30,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +35: [2022-12-02 10:52:30,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:30,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:30,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +59: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +59: [2022-12-02 10:52:30,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +59: [2022-12-02 10:52:30,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +56: [2022-12-02 10:52:30,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +49: [2022-12-02 10:52:30,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +57: [2022-12-02 10:52:30,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +37: [2022-12-02 10:52:30,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +56: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +54: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:30,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +46: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +42: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +56: [2022-12-02 10:52:30,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +32: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +46: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +38: [2022-12-02 10:52:30,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +55: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +57: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +58: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +40: [2022-12-02 10:52:30,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +32: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +40: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +40: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +56: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +40: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +34: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +39: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +61: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +58: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +54: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +54: [2022-12-02 10:52:30,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +42: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +60: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +11: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +11: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +60: [2022-12-02 10:52:30,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:30,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +52: [2022-12-02 10:52:30,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +60: [2022-12-02 10:52:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +53: [2022-12-02 10:52:30,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:30,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +53: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:30,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +33: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +36: [2022-12-02 10:52:30,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +62: [2022-12-02 10:52:30,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +62: [2022-12-02 10:52:30,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +49: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +42: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +63: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +51: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +49: [2022-12-02 10:52:30,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +49: [2022-12-02 10:52:30,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +49: [2022-12-02 10:52:30,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +49: [2022-12-02 10:52:30,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:30,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +42: [2022-12-02 10:52:30,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +47: [2022-12-02 10:52:30,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt... +45: [2022-12-02 10:52:30,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:30,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:30,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:30,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +33: [2022-12-02 10:52:30,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:30,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:30,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +51: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +40: [2022-12-02 10:52:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +40: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +40: [2022-12-02 10:52:30,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +38: [2022-12-02 10:52:30,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +39: [2022-12-02 10:52:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:30,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:30,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +57: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +55: [2022-12-02 10:52:30,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +52: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +46: [2022-12-02 10:52:30,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +11: [2022-12-02 10:52:30,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +45: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +44: [2022-12-02 10:52:30,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +45: [2022-12-02 10:52:30,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:30,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +60: [2022-12-02 10:52:30,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +61: [2022-12-02 10:52:30,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +59: [2022-12-02 10:52:30,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +63: [2022-12-02 10:52:30,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +37: [2022-12-02 10:52:30,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +11: [2022-12-02 10:52:30,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:30,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:30,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +36: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +34: [2022-12-02 10:52:30,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:30,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:30,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +57: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:30,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +34: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +29: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +40: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:30,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:30,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +57: [2022-12-02 10:52:30,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:30,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:30,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +52: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +54: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +60: [2022-12-02 10:52:30,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +38: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +47: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_23-model_00-model_states.pt. +11: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +38: [2022-12-02 10:52:30,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:30,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +54: [2022-12-02 10:52:30,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:30,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +29: [2022-12-02 10:52:30,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +46: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +17: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +46: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +23: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +60: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +23: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +54: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +29: [2022-12-02 10:52:30,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +29: [2022-12-02 10:52:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +63: [2022-12-02 10:52:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +29: [2022-12-02 10:52:30,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +60: [2022-12-02 10:52:30,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:30,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +23: [2022-12-02 10:52:30,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +60: [2022-12-02 10:52:30,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +23: [2022-12-02 10:52:30,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:30,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +60: [2022-12-02 10:52:30,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:30,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:30,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:30,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +20: [2022-12-02 10:52:30,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:30,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +61: [2022-12-02 10:52:30,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +20: [2022-12-02 10:52:30,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +61: [2022-12-02 10:52:30,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +20: [2022-12-02 10:52:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +61: [2022-12-02 10:52:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:30,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +14: [2022-12-02 10:52:30,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +36: [2022-12-02 10:52:30,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +20: [2022-12-02 10:52:30,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:30,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +36: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +14: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:30,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:30,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +36: [2022-12-02 10:52:30,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +14: [2022-12-02 10:52:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +47: [2022-12-02 10:52:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:30,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +14: [2022-12-02 10:52:30,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +47: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:30,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +17: [2022-12-02 10:52:31,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:31,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:31,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:31,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:31,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:31,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:31,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +23: [2022-12-02 10:52:31,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +23: [2022-12-02 10:52:31,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:31,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +20: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:31,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:31,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +17: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +29: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +14: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +17: [2022-12-02 10:52:31,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +20: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +14: [2022-12-02 10:52:31,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +31: [2022-12-02 10:52:31,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:31,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +31: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +41: [2022-12-02 10:52:31,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +41: [2022-12-02 10:52:31,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:31,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:31,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +41: [2022-12-02 10:52:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +41: [2022-12-02 10:52:31,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:31,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:31,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:31,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +16: [2022-12-02 10:52:31,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +30: [2022-12-02 10:52:31,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +30: [2022-12-02 10:52:31,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +12: [2022-12-02 10:52:31,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +27: [2022-12-02 10:52:31,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +27: [2022-12-02 10:52:31,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +24: [2022-12-02 10:52:31,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +15: [2022-12-02 10:52:31,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +24: [2022-12-02 10:52:31,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +15: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +18: [2022-12-02 10:52:31,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +22: [2022-12-02 10:52:31,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +22: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +16: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +18: [2022-12-02 10:52:31,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +41: [2022-12-02 10:52:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +30: [2022-12-02 10:52:31,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +41: [2022-12-02 10:52:31,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +41: [2022-12-02 10:52:31,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +30: [2022-12-02 10:52:31,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +13: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +12: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +12: [2022-12-02 10:52:31,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +12: [2022-12-02 10:52:31,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +28: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +28: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +28: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +19: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +41: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +26: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +21: [2022-12-02 10:52:31,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +26: [2022-12-02 10:52:31,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:31,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:31,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +25: [2022-12-02 10:52:31,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +26: [2022-12-02 10:52:31,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +28: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:31,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +58: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +28: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +28: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +10: [2022-12-02 10:52:31,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +58: [2022-12-02 10:52:31,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:31,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +13: [2022-12-02 10:52:31,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +12: [2022-12-02 10:52:31,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +19: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +19: [2022-12-02 10:52:31,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +21: [2022-12-02 10:52:31,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +10: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +50: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +25: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +25: [2022-12-02 10:52:31,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +10: [2022-12-02 10:52:31,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +13: [2022-12-02 10:52:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt... +50: [2022-12-02 10:52:31,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +13: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +13: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +13: [2022-12-02 10:52:31,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +58: [2022-12-02 10:52:31,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +32: [2022-12-02 10:52:31,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +26: [2022-12-02 10:52:31,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +56: [2022-12-02 10:52:31,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +26: [2022-12-02 10:52:31,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +33: [2022-12-02 10:52:31,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +28: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +33: [2022-12-02 10:52:31,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:31,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:31,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +53: [2022-12-02 10:52:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +56: [2022-12-02 10:52:31,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +56: [2022-12-02 10:52:31,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +33: [2022-12-02 10:52:31,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +38: [2022-12-02 10:52:31,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +38: [2022-12-02 10:52:31,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +38: [2022-12-02 10:52:31,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +26: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +53: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:31,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +26: [2022-12-02 10:52:31,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +58: [2022-12-02 10:52:31,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +28: [2022-12-02 10:52:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +28: [2022-12-02 10:52:31,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +26: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +43: [2022-12-02 10:52:31,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +26: [2022-12-02 10:52:31,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +26: [2022-12-02 10:52:31,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +43: [2022-12-02 10:52:31,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +28: [2022-12-02 10:52:31,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +43: [2022-12-02 10:52:31,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +28: [2022-12-02 10:52:31,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +43: [2022-12-02 10:52:31,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +26: [2022-12-02 10:52:31,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. +50: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:31,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +26: [2022-12-02 10:52:31,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_04-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +46: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:31,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:31,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +35: [2022-12-02 10:52:31,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +26: [2022-12-02 10:52:31,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +46: [2022-12-02 10:52:31,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:31,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +46: [2022-12-02 10:52:31,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:31,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:31,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:31,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +28: [2022-12-02 10:52:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +35: [2022-12-02 10:52:31,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:31,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +58: [2022-12-02 10:52:31,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +11: [2022-12-02 10:52:31,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +35: [2022-12-02 10:52:31,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:31,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:31,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:31,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +35: [2022-12-02 10:52:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +35: [2022-12-02 10:52:31,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +32: [2022-12-02 10:52:31,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +28: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +11: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +32: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +11: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +11: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +11: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +47: [2022-12-02 10:52:31,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:31,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +58: [2022-12-02 10:52:31,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:31,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:31,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:31,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +38: [2022-12-02 10:52:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +50: [2022-12-02 10:52:31,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:31,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:31,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +50: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +53: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +59: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +53: [2022-12-02 10:52:31,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +38: [2022-12-02 10:52:31,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +50: [2022-12-02 10:52:31,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +34: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +34: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +34: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +32: [2022-12-02 10:52:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:31,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +32: [2022-12-02 10:52:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +60: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +17: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +23: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +17: [2022-12-02 10:52:31,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +31: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +43: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:31,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:31,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:31,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:31,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:31,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +34: [2022-12-02 10:52:31,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:31,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +34: [2022-12-02 10:52:31,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:31,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +56: [2022-12-02 10:52:31,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:31,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +53: [2022-12-02 10:52:31,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:31,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:31,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:31,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +49: [2022-12-02 10:52:31,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +49: [2022-12-02 10:52:31,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +33: [2022-12-02 10:52:31,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +33: [2022-12-02 10:52:31,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:31,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:31,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:31,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +32: [2022-12-02 10:52:31,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:31,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:31,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:31,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +32: [2022-12-02 10:52:31,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +34: [2022-12-02 10:52:31,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +46: [2022-12-02 10:52:31,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +34: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +38: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:31,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +56: [2022-12-02 10:52:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +34: [2022-12-02 10:52:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +34: [2022-12-02 10:52:31,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:31,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +35: [2022-12-02 10:52:31,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:31,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +45: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +54: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +52: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:31,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:31,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +40: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:31,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +40: [2022-12-02 10:52:31,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +63: [2022-12-02 10:52:31,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:31,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +11: [2022-12-02 10:52:31,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +39: [2022-12-02 10:52:31,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +43: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +43: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +63: [2022-12-02 10:52:31,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +63: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +43: [2022-12-02 10:52:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:31,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +62: [2022-12-02 10:52:31,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +39: [2022-12-02 10:52:31,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +59: [2022-12-02 10:52:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +48: [2022-12-02 10:52:31,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:31,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +11: [2022-12-02 10:52:31,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:31,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +45: [2022-12-02 10:52:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:31,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:31,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +44: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +48: [2022-12-02 10:52:31,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +17: [2022-12-02 10:52:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +46: [2022-12-02 10:52:31,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +51: [2022-12-02 10:52:31,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +47: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +35: [2022-12-02 10:52:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:31,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +35: [2022-12-02 10:52:31,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +35: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +35: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +17: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +17: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +31: [2022-12-02 10:52:31,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +31: [2022-12-02 10:52:31,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +51: [2022-12-02 10:52:31,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +15: [2022-12-02 10:52:31,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +35: [2022-12-02 10:52:31,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:31,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:31,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +60: [2022-12-02 10:52:31,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +49: [2022-12-02 10:52:31,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:31,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +51: [2022-12-02 10:52:31,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +11: [2022-12-02 10:52:31,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +46: [2022-12-02 10:52:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +46: [2022-12-02 10:52:31,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +11: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +11: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +15: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +49: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +11: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +15: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +59: [2022-12-02 10:52:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:31,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +23: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:31,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +36: [2022-12-02 10:52:31,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +59: [2022-12-02 10:52:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +17: [2022-12-02 10:52:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:31,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:31,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +23: [2022-12-02 10:52:31,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +59: [2022-12-02 10:52:31,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:31,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +42: [2022-12-02 10:52:31,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +31: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +17: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +17: [2022-12-02 10:52:31,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +54: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +57: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +17: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +61: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +17: [2022-12-02 10:52:31,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:31,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +54: [2022-12-02 10:52:31,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:31,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +39: [2022-12-02 10:52:31,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +47: [2022-12-02 10:52:31,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:31,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +61: [2022-12-02 10:52:31,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +54: [2022-12-02 10:52:31,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +31: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +45: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +54: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +36: [2022-12-02 10:52:31,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +57: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +55: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +49: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +36: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +36: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +36: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +40: [2022-12-02 10:52:31,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +47: [2022-12-02 10:52:31,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:31,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +45: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +57: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +45: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +44: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +45: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:31,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +49: [2022-12-02 10:52:31,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +61: [2022-12-02 10:52:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +63: [2022-12-02 10:52:31,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +60: [2022-12-02 10:52:31,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +52: [2022-12-02 10:52:31,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +61: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +61: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt... +40: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +63: [2022-12-02 10:52:31,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +52: [2022-12-02 10:52:31,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +55: [2022-12-02 10:52:31,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:31,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +14: [2022-12-02 10:52:31,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +49: [2022-12-02 10:52:31,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +14: [2022-12-02 10:52:31,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +42: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +14: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +49: [2022-12-02 10:52:31,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:31,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +62: [2022-12-02 10:52:31,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:31,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +62: [2022-12-02 10:52:31,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:31,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +14: [2022-12-02 10:52:31,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +62: [2022-12-02 10:52:31,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:31,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +37: [2022-12-02 10:52:31,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +22: [2022-12-02 10:52:31,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +63: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +14: [2022-12-02 10:52:31,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +63: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +14: [2022-12-02 10:52:31,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +42: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:31,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +22: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +44: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +15: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +42: [2022-12-02 10:52:31,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:31,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +54: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:31,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +51: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +15: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +51: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +51: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +37: [2022-12-02 10:52:31,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +54: [2022-12-02 10:52:31,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:31,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +55: [2022-12-02 10:52:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +54: [2022-12-02 10:52:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 6: [2022-12-02 10:52:31,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +40: [2022-12-02 10:52:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 6: [2022-12-02 10:52:31,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +63: [2022-12-02 10:52:31,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:31,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:31,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +40: [2022-12-02 10:52:31,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:31,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +40: [2022-12-02 10:52:31,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:31,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:31,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +62: [2022-12-02 10:52:31,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:31,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +52: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +62: [2022-12-02 10:52:31,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:31,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +20: [2022-12-02 10:52:31,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +62: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +39: [2022-12-02 10:52:31,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +20: [2022-12-02 10:52:31,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +62: [2022-12-02 10:52:31,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +39: [2022-12-02 10:52:31,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +20: [2022-12-02 10:52:31,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +39: [2022-12-02 10:52:31,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +39: [2022-12-02 10:52:31,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:31,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +39: [2022-12-02 10:52:31,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:31,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +51: [2022-12-02 10:52:31,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +27: [2022-12-02 10:52:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +39: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +27: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +51: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +20: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +57: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +29: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +37: [2022-12-02 10:52:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +37: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +27: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +37: [2022-12-02 10:52:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:31,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +57: [2022-12-02 10:52:31,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +44: [2022-12-02 10:52:31,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:31,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +10: [2022-12-02 10:52:31,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +15: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +15: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +15: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +51: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +44: [2022-12-02 10:52:31,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +51: [2022-12-02 10:52:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +16: [2022-12-02 10:52:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +51: [2022-12-02 10:52:31,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +16: [2022-12-02 10:52:31,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +16: [2022-12-02 10:52:31,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +36: [2022-12-02 10:52:31,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +16: [2022-12-02 10:52:31,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +15: [2022-12-02 10:52:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +15: [2022-12-02 10:52:31,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +36: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +24: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +36: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +24: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +36: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +36: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +10: [2022-12-02 10:52:31,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +61: [2022-12-02 10:52:31,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. + 8: [2022-12-02 10:52:31,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:31,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +61: [2022-12-02 10:52:31,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_24-model_00-model_states.pt. +61: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +24: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +14: [2022-12-02 10:52:31,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +22: [2022-12-02 10:52:31,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +57: [2022-12-02 10:52:31,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:31,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +57: [2022-12-02 10:52:31,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:31,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:31,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +13: [2022-12-02 10:52:31,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 7: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:31,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:31,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:31,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +57: [2022-12-02 10:52:31,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +30: [2022-12-02 10:52:31,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +61: [2022-12-02 10:52:31,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +36: [2022-12-02 10:52:31,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +14: [2022-12-02 10:52:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:31,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:31,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:31,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:31,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:31,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:31,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:31,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:31,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:31,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:31,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +36: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +29: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +61: [2022-12-02 10:52:31,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:31,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +20: [2022-12-02 10:52:31,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +61: [2022-12-02 10:52:31,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +29: [2022-12-02 10:52:31,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +61: [2022-12-02 10:52:31,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +29: [2022-12-02 10:52:31,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +61: [2022-12-02 10:52:31,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:31,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +61: [2022-12-02 10:52:31,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:31,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +20: [2022-12-02 10:52:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +22: [2022-12-02 10:52:31,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:31,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:31,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 9: [2022-12-02 10:52:31,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +27: [2022-12-02 10:52:31,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +20: [2022-12-02 10:52:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +29: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:31,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +29: [2022-12-02 10:52:31,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:31,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:31,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:31,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:31,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:31,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:31,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:31,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +20: [2022-12-02 10:52:31,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:31,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +16: [2022-12-02 10:52:31,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:31,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 0: [2022-12-02 10:52:31,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:31,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:31,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:31,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +25: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:31,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +27: [2022-12-02 10:52:31,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:31,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +10: [2022-12-02 10:52:31,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:31,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +24: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +10: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:31,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +12: [2022-12-02 10:52:31,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 3: [2022-12-02 10:52:31,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +24: [2022-12-02 10:52:31,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:31,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:31,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:31,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +18: [2022-12-02 10:52:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +21: [2022-12-02 10:52:31,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +28: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +30: [2022-12-02 10:52:31,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:31,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:31,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:31,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:31,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:31,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +18: [2022-12-02 10:52:31,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +13: [2022-12-02 10:52:31,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +26: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +19: [2022-12-02 10:52:31,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt... +13: [2022-12-02 10:52:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:31,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:31,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:31,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:31,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:31,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +30: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +30: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:31,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:31,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +30: [2022-12-02 10:52:31,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +30: [2022-12-02 10:52:31,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:31,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +41: [2022-12-02 10:52:31,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +25: [2022-12-02 10:52:31,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +41: [2022-12-02 10:52:31,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:31,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +12: [2022-12-02 10:52:31,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +41: [2022-12-02 10:52:31,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:31,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +19: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +19: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:31,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 4: [2022-12-02 10:52:31,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:31,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:31,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +53: [2022-12-02 10:52:31,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:31,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +26: [2022-12-02 10:52:31,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:31,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +21: [2022-12-02 10:52:31,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +53: [2022-12-02 10:52:31,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +25: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +53: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +25: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +53: [2022-12-02 10:52:31,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +26: [2022-12-02 10:52:31,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:31,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +25: [2022-12-02 10:52:31,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:31,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:31,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +58: [2022-12-02 10:52:31,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +28: [2022-12-02 10:52:31,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:31,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +28: [2022-12-02 10:52:31,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:31,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:31,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:31,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +58: [2022-12-02 10:52:31,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:31,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:31,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 1: [2022-12-02 10:52:31,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:31,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +58: [2022-12-02 10:52:32,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +21: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +12: [2022-12-02 10:52:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. +26: [2022-12-02 10:52:32,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +35: [2022-12-02 10:52:32,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_05-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +58: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +21: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +58: [2022-12-02 10:52:32,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +50: [2022-12-02 10:52:32,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +26: [2022-12-02 10:52:32,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +21: [2022-12-02 10:52:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +35: [2022-12-02 10:52:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:32,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:32,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:32,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +21: [2022-12-02 10:52:32,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +41: [2022-12-02 10:52:32,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +50: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +28: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +50: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +28: [2022-12-02 10:52:32,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +32: [2022-12-02 10:52:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:32,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:32,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +41: [2022-12-02 10:52:32,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:32,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +41: [2022-12-02 10:52:32,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:32,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +53: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +50: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +53: [2022-12-02 10:52:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +56: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +31: [2022-12-02 10:52:32,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +38: [2022-12-02 10:52:32,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +31: [2022-12-02 10:52:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +45: [2022-12-02 10:52:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +35: [2022-12-02 10:52:32,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +34: [2022-12-02 10:52:32,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +35: [2022-12-02 10:52:32,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:32,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:32,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:32,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +58: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +50: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +34: [2022-12-02 10:52:32,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +32: [2022-12-02 10:52:32,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +58: [2022-12-02 10:52:32,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +45: [2022-12-02 10:52:32,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +43: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +43: [2022-12-02 10:52:32,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +43: [2022-12-02 10:52:32,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:32,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +15: [2022-12-02 10:52:32,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +46: [2022-12-02 10:52:32,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +17: [2022-12-02 10:52:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +46: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:32,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +54: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +51: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +23: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +33: [2022-12-02 10:52:32,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +33: [2022-12-02 10:52:32,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +15: [2022-12-02 10:52:32,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +47: [2022-12-02 10:52:32,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +31: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +33: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +31: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +33: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +15: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +63: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +63: [2022-12-02 10:52:32,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +15: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +32: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +33: [2022-12-02 10:52:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +51: [2022-12-02 10:52:32,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +47: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +31: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +60: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:32,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +59: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +39: [2022-12-02 10:52:32,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +23: [2022-12-02 10:52:32,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:32,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:32,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +63: [2022-12-02 10:52:32,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +11: [2022-12-02 10:52:32,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +63: [2022-12-02 10:52:32,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:32,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +56: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +56: [2022-12-02 10:52:32,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +38: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +45: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +48: [2022-12-02 10:52:32,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:32,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:32,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +47: [2022-12-02 10:52:32,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +11: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +55: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +55: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +49: [2022-12-02 10:52:32,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +49: [2022-12-02 10:52:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +11: [2022-12-02 10:52:32,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +11: [2022-12-02 10:52:32,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +11: [2022-12-02 10:52:32,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +11: [2022-12-02 10:52:32,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +34: [2022-12-02 10:52:32,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +48: [2022-12-02 10:52:32,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +48: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:32,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:32,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +56: [2022-12-02 10:52:32,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +49: [2022-12-02 10:52:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +36: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +31: [2022-12-02 10:52:32,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +44: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +36: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +44: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +22: [2022-12-02 10:52:32,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +44: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +44: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +37: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +22: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +44: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +44: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +37: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:32,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +31: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +37: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +46: [2022-12-02 10:52:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +46: [2022-12-02 10:52:32,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:32,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +38: [2022-12-02 10:52:32,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +40: [2022-12-02 10:52:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +22: [2022-12-02 10:52:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:32,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +38: [2022-12-02 10:52:32,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +31: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +56: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +22: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +38: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +40: [2022-12-02 10:52:32,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:32,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +40: [2022-12-02 10:52:32,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:32,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:32,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +40: [2022-12-02 10:52:32,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +56: [2022-12-02 10:52:32,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +38: [2022-12-02 10:52:32,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +17: [2022-12-02 10:52:32,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +54: [2022-12-02 10:52:32,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +17: [2022-12-02 10:52:32,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +34: [2022-12-02 10:52:32,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +27: [2022-12-02 10:52:32,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +34: [2022-12-02 10:52:32,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +39: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +34: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +15: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +34: [2022-12-02 10:52:32,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +17: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +17: [2022-12-02 10:52:32,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +54: [2022-12-02 10:52:32,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +27: [2022-12-02 10:52:32,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +60: [2022-12-02 10:52:32,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:32,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +52: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +52: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +57: [2022-12-02 10:52:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +59: [2022-12-02 10:52:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +27: [2022-12-02 10:52:32,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +23: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +23: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +51: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +23: [2022-12-02 10:52:32,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +63: [2022-12-02 10:52:32,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +23: [2022-12-02 10:52:32,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +59: [2022-12-02 10:52:32,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +60: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +42: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +57: [2022-12-02 10:52:32,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +57: [2022-12-02 10:52:32,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +63: [2022-12-02 10:52:32,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +54: [2022-12-02 10:52:32,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +54: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +39: [2022-12-02 10:52:32,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +62: [2022-12-02 10:52:32,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +55: [2022-12-02 10:52:32,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +17: [2022-12-02 10:52:32,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:32,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +17: [2022-12-02 10:52:32,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +47: [2022-12-02 10:52:32,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +62: [2022-12-02 10:52:32,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +17: [2022-12-02 10:52:32,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +49: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +47: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +11: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +47: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +37: [2022-12-02 10:52:32,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +61: [2022-12-02 10:52:32,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt... +11: [2022-12-02 10:52:32,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:32,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +17: [2022-12-02 10:52:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:32,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +17: [2022-12-02 10:52:32,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +51: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +51: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +23: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:32,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +23: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +63: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +23: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +15: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +49: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +49: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +15: [2022-12-02 10:52:32,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +59: [2022-12-02 10:52:32,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +63: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +22: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +22: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +60: [2022-12-02 10:52:32,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +20: [2022-12-02 10:52:32,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +59: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +37: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +11: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +11: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +60: [2022-12-02 10:52:32,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +63: [2022-12-02 10:52:32,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +60: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +22: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +22: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +59: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +59: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +51: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +63: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +44: [2022-12-02 10:52:32,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +51: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +40: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +42: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +20: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +59: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +20: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +36: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +20: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +59: [2022-12-02 10:52:32,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +42: [2022-12-02 10:52:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +20: [2022-12-02 10:52:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +42: [2022-12-02 10:52:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +20: [2022-12-02 10:52:32,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +55: [2022-12-02 10:52:32,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:32,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:32,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:32,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +55: [2022-12-02 10:52:32,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +55: [2022-12-02 10:52:32,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +44: [2022-12-02 10:52:32,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +44: [2022-12-02 10:52:32,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +11: [2022-12-02 10:52:32,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +47: [2022-12-02 10:52:32,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 6: [2022-12-02 10:52:32,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +39: [2022-12-02 10:52:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +11: [2022-12-02 10:52:32,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +11: [2022-12-02 10:52:32,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +11: [2022-12-02 10:52:32,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +62: [2022-12-02 10:52:32,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +11: [2022-12-02 10:52:32,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +49: [2022-12-02 10:52:32,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +47: [2022-12-02 10:52:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:32,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +47: [2022-12-02 10:52:32,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +49: [2022-12-02 10:52:32,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +49: [2022-12-02 10:52:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +40: [2022-12-02 10:52:32,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +37: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +52: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:32,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +52: [2022-12-02 10:52:32,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +37: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +40: [2022-12-02 10:52:32,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +40: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +44: [2022-12-02 10:52:32,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +57: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +44: [2022-12-02 10:52:32,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +44: [2022-12-02 10:52:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +40: [2022-12-02 10:52:32,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +40: [2022-12-02 10:52:32,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +44: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +44: [2022-12-02 10:52:32,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +52: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +36: [2022-12-02 10:52:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 6: [2022-12-02 10:52:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +52: [2022-12-02 10:52:32,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +10: [2022-12-02 10:52:32,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +24: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +36: [2022-12-02 10:52:32,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +10: [2022-12-02 10:52:32,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +52: [2022-12-02 10:52:32,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +10: [2022-12-02 10:52:32,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:32,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +57: [2022-12-02 10:52:32,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +57: [2022-12-02 10:52:32,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +29: [2022-12-02 10:52:32,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +52: [2022-12-02 10:52:32,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +13: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +52: [2022-12-02 10:52:32,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +20: [2022-12-02 10:52:32,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +57: [2022-12-02 10:52:32,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +57: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +61: [2022-12-02 10:52:32,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_25-model_00-model_states.pt. +57: [2022-12-02 10:52:32,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +57: [2022-12-02 10:52:32,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +57: [2022-12-02 10:52:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +13: [2022-12-02 10:52:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +52: [2022-12-02 10:52:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +57: [2022-12-02 10:52:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +27: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +13: [2022-12-02 10:52:32,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +27: [2022-12-02 10:52:32,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:32,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:32,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:32,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:32,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +61: [2022-12-02 10:52:32,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:32,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +61: [2022-12-02 10:52:32,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +16: [2022-12-02 10:52:32,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +61: [2022-12-02 10:52:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +61: [2022-12-02 10:52:32,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +19: [2022-12-02 10:52:32,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:32,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +61: [2022-12-02 10:52:32,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +24: [2022-12-02 10:52:32,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 9: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +61: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +19: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +20: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 9: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +20: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:32,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:32,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:32,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +25: [2022-12-02 10:52:32,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:32,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:32,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +30: [2022-12-02 10:52:32,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +24: [2022-12-02 10:52:32,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:32,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +16: [2022-12-02 10:52:32,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +16: [2022-12-02 10:52:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +24: [2022-12-02 10:52:32,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +25: [2022-12-02 10:52:32,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:32,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +28: [2022-12-02 10:52:32,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +10: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +29: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +12: [2022-12-02 10:52:32,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +18: [2022-12-02 10:52:32,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +10: [2022-12-02 10:52:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +29: [2022-12-02 10:52:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +13: [2022-12-02 10:52:32,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 0: [2022-12-02 10:52:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +19: [2022-12-02 10:52:32,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +18: [2022-12-02 10:52:32,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +53: [2022-12-02 10:52:32,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +18: [2022-12-02 10:52:32,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:32,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +18: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +14: [2022-12-02 10:52:32,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:32,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:32,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +19: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +26: [2022-12-02 10:52:32,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:32,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +14: [2022-12-02 10:52:32,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:32,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +12: [2022-12-02 10:52:32,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 1: [2022-12-02 10:52:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:32,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +28: [2022-12-02 10:52:32,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +30: [2022-12-02 10:52:32,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +50: [2022-12-02 10:52:32,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +26: [2022-12-02 10:52:32,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +50: [2022-12-02 10:52:32,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +30: [2022-12-02 10:52:32,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:32,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +50: [2022-12-02 10:52:32,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +12: [2022-12-02 10:52:32,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +50: [2022-12-02 10:52:32,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +26: [2022-12-02 10:52:32,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +50: [2022-12-02 10:52:32,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +12: [2022-12-02 10:52:32,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:32,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +28: [2022-12-02 10:52:32,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:32,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:32,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:32,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +28: [2022-12-02 10:52:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 5: [2022-12-02 10:52:32,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:32,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +26: [2022-12-02 10:52:32,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:32,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +35: [2022-12-02 10:52:32,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +35: [2022-12-02 10:52:32,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +48: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +48: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +48: [2022-12-02 10:52:32,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +58: [2022-12-02 10:52:32,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +53: [2022-12-02 10:52:32,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:32,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +43: [2022-12-02 10:52:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +21: [2022-12-02 10:52:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +34: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +21: [2022-12-02 10:52:32,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +34: [2022-12-02 10:52:32,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:32,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +53: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +21: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +45: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +21: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt... +34: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +43: [2022-12-02 10:52:32,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +34: [2022-12-02 10:52:32,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +46: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +50: [2022-12-02 10:52:32,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +56: [2022-12-02 10:52:32,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +32: [2022-12-02 10:52:32,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +32: [2022-12-02 10:52:32,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 2: [2022-12-02 10:52:32,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:32,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:32,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:32,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:32,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:32,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +58: [2022-12-02 10:52:32,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:32,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +50: [2022-12-02 10:52:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:32,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +41: [2022-12-02 10:52:32,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +21: [2022-12-02 10:52:32,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +41: [2022-12-02 10:52:32,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +41: [2022-12-02 10:52:32,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:32,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +43: [2022-12-02 10:52:32,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +21: [2022-12-02 10:52:32,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +21: [2022-12-02 10:52:32,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_06-model_00-model_states.pt. +58: [2022-12-02 10:52:32,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +63: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +63: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +48: [2022-12-02 10:52:32,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +48: [2022-12-02 10:52:32,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +35: [2022-12-02 10:52:32,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:32,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +56: [2022-12-02 10:52:32,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:32,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:32,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +21: [2022-12-02 10:52:32,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +32: [2022-12-02 10:52:32,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:32,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +34: [2022-12-02 10:52:32,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:32,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +43: [2022-12-02 10:52:32,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:32,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:32,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:32,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:32,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +43: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +46: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +21: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:32,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +58: [2022-12-02 10:52:32,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:32,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +34: [2022-12-02 10:52:32,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +58: [2022-12-02 10:52:32,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:32,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:32,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +46: [2022-12-02 10:52:32,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:32,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +33: [2022-12-02 10:52:32,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +45: [2022-12-02 10:52:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +56: [2022-12-02 10:52:32,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:32,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:32,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +51: [2022-12-02 10:52:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +45: [2022-12-02 10:52:32,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +32: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +32: [2022-12-02 10:52:32,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:32,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +17: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +32: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +17: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +47: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +32: [2022-12-02 10:52:32,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:32,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +17: [2022-12-02 10:52:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +42: [2022-12-02 10:52:32,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +61: [2022-12-02 10:52:32,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +38: [2022-12-02 10:52:32,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +22: [2022-12-02 10:52:32,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +52: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +38: [2022-12-02 10:52:32,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +59: [2022-12-02 10:52:32,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +42: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +42: [2022-12-02 10:52:32,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +47: [2022-12-02 10:52:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +38: [2022-12-02 10:52:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:32,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +22: [2022-12-02 10:52:32,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +52: [2022-12-02 10:52:32,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +22: [2022-12-02 10:52:32,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +33: [2022-12-02 10:52:32,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +22: [2022-12-02 10:52:32,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:32,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +60: [2022-12-02 10:52:32,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +31: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +52: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +31: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +52: [2022-12-02 10:52:32,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +52: [2022-12-02 10:52:32,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +33: [2022-12-02 10:52:32,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:32,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:32,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +31: [2022-12-02 10:52:32,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +40: [2022-12-02 10:52:32,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +60: [2022-12-02 10:52:32,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +44: [2022-12-02 10:52:32,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:32,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +37: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +37: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +40: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:32,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +62: [2022-12-02 10:52:32,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +62: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +55: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +55: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +55: [2022-12-02 10:52:32,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:32,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +55: [2022-12-02 10:52:32,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +44: [2022-12-02 10:52:32,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:32,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:32,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +59: [2022-12-02 10:52:32,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:32,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +59: [2022-12-02 10:52:32,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +27: [2022-12-02 10:52:32,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:32,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... + 4: [2022-12-02 10:52:32,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:32,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 8: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:32,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +36: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +27: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:32,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +51: [2022-12-02 10:52:32,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +23: [2022-12-02 10:52:32,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +61: [2022-12-02 10:52:32,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +23: [2022-12-02 10:52:32,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:32,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +23: [2022-12-02 10:52:32,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +51: [2022-12-02 10:52:32,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:32,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +10: [2022-12-02 10:52:32,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:32,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +54: [2022-12-02 10:52:32,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +23: [2022-12-02 10:52:32,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +47: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +17: [2022-12-02 10:52:32,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:32,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:32,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:32,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:32,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:32,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:32,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:32,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +44: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +44: [2022-12-02 10:52:32,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +10: [2022-12-02 10:52:32,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +44: [2022-12-02 10:52:32,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +13: [2022-12-02 10:52:32,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +44: [2022-12-02 10:52:32,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:32,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +13: [2022-12-02 10:52:32,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:32,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +42: [2022-12-02 10:52:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:32,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +61: [2022-12-02 10:52:32,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:32,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:32,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +52: [2022-12-02 10:52:32,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:32,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +51: [2022-12-02 10:52:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +51: [2022-12-02 10:52:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +61: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 3: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:32,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +61: [2022-12-02 10:52:32,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:32,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +52: [2022-12-02 10:52:32,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +51: [2022-12-02 10:52:32,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +31: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +51: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +17: [2022-12-02 10:52:32,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +62: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +62: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:32,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +60: [2022-12-02 10:52:32,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +47: [2022-12-02 10:52:32,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:32,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +31: [2022-12-02 10:52:32,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:32,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:32,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +51: [2022-12-02 10:52:32,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:32,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:32,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:32,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +29: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +17: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:32,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:32,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:32,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +40: [2022-12-02 10:52:32,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +24: [2022-12-02 10:52:32,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:32,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:32,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +37: [2022-12-02 10:52:32,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:32,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +15: [2022-12-02 10:52:32,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +40: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +40: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +17: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +17: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:32,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +55: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:32,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +27: [2022-12-02 10:52:32,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:32,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:32,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:32,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:32,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:32,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:33,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +55: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +55: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +55: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +61: [2022-12-02 10:52:33,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +22: [2022-12-02 10:52:33,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:33,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:33,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +60: [2022-12-02 10:52:33,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +15: [2022-12-02 10:52:33,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +15: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +15: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +22: [2022-12-02 10:52:33,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +62: [2022-12-02 10:52:33,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:33,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +15: [2022-12-02 10:52:33,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +22: [2022-12-02 10:52:33,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +42: [2022-12-02 10:52:33,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +15: [2022-12-02 10:52:33,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:33,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:33,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +52: [2022-12-02 10:52:33,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +62: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +62: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +22: [2022-12-02 10:52:33,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +42: [2022-12-02 10:52:33,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:33,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +42: [2022-12-02 10:52:33,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +31: [2022-12-02 10:52:33,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +47: [2022-12-02 10:52:33,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +23: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +60: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +60: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +23: [2022-12-02 10:52:33,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +31: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:33,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +61: [2022-12-02 10:52:33,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +31: [2022-12-02 10:52:33,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +47: [2022-12-02 10:52:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +27: [2022-12-02 10:52:33,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:33,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:33,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +60: [2022-12-02 10:52:33,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +31: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +61: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +23: [2022-12-02 10:52:33,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +61: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +31: [2022-12-02 10:52:33,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +47: [2022-12-02 10:52:33,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +11: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +10: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +27: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +52: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +20: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +36: [2022-12-02 10:52:33,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +61: [2022-12-02 10:52:33,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +13: [2022-12-02 10:52:33,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +55: [2022-12-02 10:52:33,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +52: [2022-12-02 10:52:33,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +55: [2022-12-02 10:52:33,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +37: [2022-12-02 10:52:33,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +11: [2022-12-02 10:52:33,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +39: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:33,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +39: [2022-12-02 10:52:33,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:33,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:33,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +55: [2022-12-02 10:52:33,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +16: [2022-12-02 10:52:33,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +40: [2022-12-02 10:52:33,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +10: [2022-12-02 10:52:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +40: [2022-12-02 10:52:33,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +20: [2022-12-02 10:52:33,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:33,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +16: [2022-12-02 10:52:33,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:33,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +16: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +40: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +20: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +60: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +10: [2022-12-02 10:52:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +40: [2022-12-02 10:52:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +20: [2022-12-02 10:52:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +40: [2022-12-02 10:52:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +20: [2022-12-02 10:52:33,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +37: [2022-12-02 10:52:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +20: [2022-12-02 10:52:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +55: [2022-12-02 10:52:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +55: [2022-12-02 10:52:33,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +40: [2022-12-02 10:52:33,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +55: [2022-12-02 10:52:33,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +62: [2022-12-02 10:52:33,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +13: [2022-12-02 10:52:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:33,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:33,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +13: [2022-12-02 10:52:33,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +57: [2022-12-02 10:52:33,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +62: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +62: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +23: [2022-12-02 10:52:33,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +54: [2022-12-02 10:52:33,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:33,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +57: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +23: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +39: [2022-12-02 10:52:33,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +23: [2022-12-02 10:52:33,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +23: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +27: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +13: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +10: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:33,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +24: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +39: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +14: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +57: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +14: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +14: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +23: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +57: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +39: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +13: [2022-12-02 10:52:33,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +54: [2022-12-02 10:52:33,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +10: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +29: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +57: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +57: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +12: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +57: [2022-12-02 10:52:33,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +27: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +54: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +27: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +54: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +14: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +12: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:33,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +25: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:33,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +18: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:33,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +10: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:33,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +14: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +10: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +24: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +15: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +18: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +36: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +26: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +36: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:33,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +18: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +13: [2022-12-02 10:52:33,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +24: [2022-12-02 10:52:33,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:33,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +29: [2022-12-02 10:52:33,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +29: [2022-12-02 10:52:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +49: [2022-12-02 10:52:33,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +20: [2022-12-02 10:52:33,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +15: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +15: [2022-12-02 10:52:33,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:33,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +15: [2022-12-02 10:52:33,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +15: [2022-12-02 10:52:33,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:33,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:33,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:33,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +49: [2022-12-02 10:52:33,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt... +20: [2022-12-02 10:52:33,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +12: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +25: [2022-12-02 10:52:33,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +57: [2022-12-02 10:52:33,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +57: [2022-12-02 10:52:33,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +18: [2022-12-02 10:52:33,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +14: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +11: [2022-12-02 10:52:33,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +16: [2022-12-02 10:52:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +18: [2022-12-02 10:52:33,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +20: [2022-12-02 10:52:33,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +26: [2022-12-02 10:52:33,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +26: [2022-12-02 10:52:33,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +12: [2022-12-02 10:52:33,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +12: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +50: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +25: [2022-12-02 10:52:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +26: [2022-12-02 10:52:33,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +18: [2022-12-02 10:52:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +12: [2022-12-02 10:52:33,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:33,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:33,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:33,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +14: [2022-12-02 10:52:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +18: [2022-12-02 10:52:33,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +26: [2022-12-02 10:52:33,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +18: [2022-12-02 10:52:33,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. +49: [2022-12-02 10:52:33,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_26-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +30: [2022-12-02 10:52:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +21: [2022-12-02 10:52:33,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +19: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:33,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +19: [2022-12-02 10:52:33,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:33,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:33,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:33,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +19: [2022-12-02 10:52:33,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +21: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +41: [2022-12-02 10:52:33,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +49: [2022-12-02 10:52:33,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +58: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +58: [2022-12-02 10:52:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +28: [2022-12-02 10:52:33,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +30: [2022-12-02 10:52:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +28: [2022-12-02 10:52:33,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt... +50: [2022-12-02 10:52:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +30: [2022-12-02 10:52:33,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +35: [2022-12-02 10:52:33,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +30: [2022-12-02 10:52:33,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +35: [2022-12-02 10:52:33,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +30: [2022-12-02 10:52:33,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +35: [2022-12-02 10:52:33,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +30: [2022-12-02 10:52:33,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +35: [2022-12-02 10:52:33,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +58: [2022-12-02 10:52:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +28: [2022-12-02 10:52:33,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +32: [2022-12-02 10:52:33,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +28: [2022-12-02 10:52:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +50: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +53: [2022-12-02 10:52:33,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:33,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +28: [2022-12-02 10:52:33,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +38: [2022-12-02 10:52:33,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +28: [2022-12-02 10:52:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +32: [2022-12-02 10:52:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +32: [2022-12-02 10:52:33,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +45: [2022-12-02 10:52:33,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +19: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +45: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +50: [2022-12-02 10:52:33,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:33,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +50: [2022-12-02 10:52:33,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:33,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +19: [2022-12-02 10:52:33,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +48: [2022-12-02 10:52:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:33,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +38: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +21: [2022-12-02 10:52:33,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +63: [2022-12-02 10:52:33,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +41: [2022-12-02 10:52:33,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +19: [2022-12-02 10:52:33,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +19: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +41: [2022-12-02 10:52:33,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +28: [2022-12-02 10:52:33,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +41: [2022-12-02 10:52:33,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +21: [2022-12-02 10:52:33,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +21: [2022-12-02 10:52:33,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +28: [2022-12-02 10:52:33,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +58: [2022-12-02 10:52:33,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +28: [2022-12-02 10:52:33,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +59: [2022-12-02 10:52:33,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +28: [2022-12-02 10:52:33,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +59: [2022-12-02 10:52:33,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +28: [2022-12-02 10:52:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +33: [2022-12-02 10:52:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_07-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +33: [2022-12-02 10:52:33,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +19: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +41: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +19: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +35: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +21: [2022-12-02 10:52:33,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +41: [2022-12-02 10:52:33,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +19: [2022-12-02 10:52:33,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +41: [2022-12-02 10:52:33,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +19: [2022-12-02 10:52:33,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +41: [2022-12-02 10:52:33,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +58: [2022-12-02 10:52:33,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +21: [2022-12-02 10:52:33,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +58: [2022-12-02 10:52:33,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +58: [2022-12-02 10:52:33,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:33,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +41: [2022-12-02 10:52:33,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:33,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:33,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +48: [2022-12-02 10:52:33,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +63: [2022-12-02 10:52:33,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +56: [2022-12-02 10:52:33,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:33,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +48: [2022-12-02 10:52:33,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +35: [2022-12-02 10:52:33,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +35: [2022-12-02 10:52:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +45: [2022-12-02 10:52:33,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:33,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:33,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:33,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +58: [2022-12-02 10:52:33,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:33,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:33,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +53: [2022-12-02 10:52:33,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +34: [2022-12-02 10:52:33,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +34: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +63: [2022-12-02 10:52:33,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +32: [2022-12-02 10:52:33,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +48: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:33,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:33,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:33,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:33,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +38: [2022-12-02 10:52:33,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:33,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +38: [2022-12-02 10:52:33,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +63: [2022-12-02 10:52:33,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:33,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +59: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +59: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:33,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:33,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +45: [2022-12-02 10:52:33,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:33,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:33,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:33,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +33: [2022-12-02 10:52:33,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +42: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +33: [2022-12-02 10:52:33,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:33,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:33,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:33,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:33,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:33,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:33,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:33,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +34: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:33,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +46: [2022-12-02 10:52:33,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:33,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:33,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +51: [2022-12-02 10:52:33,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +56: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +56: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +52: [2022-12-02 10:52:33,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +46: [2022-12-02 10:52:33,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:33,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +40: [2022-12-02 10:52:33,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +34: [2022-12-02 10:52:33,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +62: [2022-12-02 10:52:33,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:33,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +39: [2022-12-02 10:52:33,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +44: [2022-12-02 10:52:33,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +34: [2022-12-02 10:52:33,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +34: [2022-12-02 10:52:33,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +47: [2022-12-02 10:52:33,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +60: [2022-12-02 10:52:33,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:33,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +54: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +43: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +62: [2022-12-02 10:52:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +57: [2022-12-02 10:52:33,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +61: [2022-12-02 10:52:33,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +43: [2022-12-02 10:52:33,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:33,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:33,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:33,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +60: [2022-12-02 10:52:33,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:33,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:33,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:33,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:33,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +44: [2022-12-02 10:52:33,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +51: [2022-12-02 10:52:33,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +42: [2022-12-02 10:52:33,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:33,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:33,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +40: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +39: [2022-12-02 10:52:33,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +36: [2022-12-02 10:52:33,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:33,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +36: [2022-12-02 10:52:33,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:33,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +37: [2022-12-02 10:52:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +36: [2022-12-02 10:52:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:33,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +51: [2022-12-02 10:52:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:33,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +36: [2022-12-02 10:52:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +61: [2022-12-02 10:52:33,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:33,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:33,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +47: [2022-12-02 10:52:33,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +39: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +39: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +39: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +12: [2022-12-02 10:52:33,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +47: [2022-12-02 10:52:33,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:33,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +52: [2022-12-02 10:52:33,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +12: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +40: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +12: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +12: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +12: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +55: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +40: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +57: [2022-12-02 10:52:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +55: [2022-12-02 10:52:33,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:33,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +24: [2022-12-02 10:52:33,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +40: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +40: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +57: [2022-12-02 10:52:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +40: [2022-12-02 10:52:33,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +40: [2022-12-02 10:52:33,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +52: [2022-12-02 10:52:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +40: [2022-12-02 10:52:33,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +10: [2022-12-02 10:52:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +52: [2022-12-02 10:52:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +24: [2022-12-02 10:52:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +55: [2022-12-02 10:52:33,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +24: [2022-12-02 10:52:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +49: [2022-12-02 10:52:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +49: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +49: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt... +55: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +10: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +10: [2022-12-02 10:52:33,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +10: [2022-12-02 10:52:33,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +16: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +39: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +54: [2022-12-02 10:52:33,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +16: [2022-12-02 10:52:33,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +16: [2022-12-02 10:52:33,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +57: [2022-12-02 10:52:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +54: [2022-12-02 10:52:33,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:33,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:33,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +54: [2022-12-02 10:52:33,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:33,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:33,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +57: [2022-12-02 10:52:33,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:33,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +37: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +20: [2022-12-02 10:52:33,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +49: [2022-12-02 10:52:33,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:33,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +24: [2022-12-02 10:52:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +49: [2022-12-02 10:52:33,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +27: [2022-12-02 10:52:33,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:33,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:33,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +24: [2022-12-02 10:52:33,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +11: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +11: [2022-12-02 10:52:33,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +49: [2022-12-02 10:52:33,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +37: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +49: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +49: [2022-12-02 10:52:33,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_27-model_00-model_states.pt. +10: [2022-12-02 10:52:33,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +37: [2022-12-02 10:52:33,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +16: [2022-12-02 10:52:33,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +31: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +12: [2022-12-02 10:52:33,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:33,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:33,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:33,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +11: [2022-12-02 10:52:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +12: [2022-12-02 10:52:33,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:33,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:33,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:33,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:33,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:33,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 7: [2022-12-02 10:52:33,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:33,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +24: [2022-12-02 10:52:33,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +24: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +49: [2022-12-02 10:52:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 3: [2022-12-02 10:52:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:33,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:33,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +24: [2022-12-02 10:52:33,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +24: [2022-12-02 10:52:33,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:33,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +11: [2022-12-02 10:52:33,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:33,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +24: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +24: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +11: [2022-12-02 10:52:33,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:33,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:33,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:33,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:33,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +10: [2022-12-02 10:52:33,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:33,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:33,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:33,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:33,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:33,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +16: [2022-12-02 10:52:33,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:33,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +31: [2022-12-02 10:52:33,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:33,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +13: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +20: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:33,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 8: [2022-12-02 10:52:33,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +18: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 8: [2022-12-02 10:52:33,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +20: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +22: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +14: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +15: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +17: [2022-12-02 10:52:33,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +23: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +29: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +30: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +25: [2022-12-02 10:52:33,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +26: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +17: [2022-12-02 10:52:33,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:33,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:33,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +19: [2022-12-02 10:52:33,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 1: [2022-12-02 10:52:33,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 1: [2022-12-02 10:52:33,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +28: [2022-12-02 10:52:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +27: [2022-12-02 10:52:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:33,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:33,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +50: [2022-12-02 10:52:33,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +50: [2022-12-02 10:52:33,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +50: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +50: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +50: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 2: [2022-12-02 10:52:33,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:33,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +50: [2022-12-02 10:52:33,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +21: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +50: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +50: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +50: [2022-12-02 10:52:33,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +50: [2022-12-02 10:52:33,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +22: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +27: [2022-12-02 10:52:33,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +32: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +32: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +32: [2022-12-02 10:52:33,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt... +32: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +32: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +26: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +32: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +25: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +32: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:33,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +23: [2022-12-02 10:52:33,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 6: [2022-12-02 10:52:33,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:33,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 4: [2022-12-02 10:52:33,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +14: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +23: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +22: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +15: [2022-12-02 10:52:33,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +25: [2022-12-02 10:52:33,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:33,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +58: [2022-12-02 10:52:33,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:33,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +26: [2022-12-02 10:52:33,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +58: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +58: [2022-12-02 10:52:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +30: [2022-12-02 10:52:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +19: [2022-12-02 10:52:33,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +58: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +30: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +30: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:33,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +18: [2022-12-02 10:52:33,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:33,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +59: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 9: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +59: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +22: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +58: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +15: [2022-12-02 10:52:33,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +58: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +58: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +13: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +58: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +22: [2022-12-02 10:52:33,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +59: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +28: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +29: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +59: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +59: [2022-12-02 10:52:33,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +14: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +28: [2022-12-02 10:52:33,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +13: [2022-12-02 10:52:33,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:33,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:33,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:33,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:33,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:33,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:33,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:33,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:33,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:33,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +26: [2022-12-02 10:52:33,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:33,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +50: [2022-12-02 10:52:33,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:33,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:33,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +50: [2022-12-02 10:52:33,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:33,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +50: [2022-12-02 10:52:33,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:33,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:33,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:33,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +48: [2022-12-02 10:52:33,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:33,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +48: [2022-12-02 10:52:33,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +48: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +30: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +21: [2022-12-02 10:52:33,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +32: [2022-12-02 10:52:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +30: [2022-12-02 10:52:33,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:33,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +32: [2022-12-02 10:52:33,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 0: [2022-12-02 10:52:33,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +48: [2022-12-02 10:52:33,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +48: [2022-12-02 10:52:33,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 5: [2022-12-02 10:52:33,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. + 5: [2022-12-02 10:52:33,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_08-model_00-model_states.pt. +48: [2022-12-02 10:52:33,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +35: [2022-12-02 10:52:33,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +32: [2022-12-02 10:52:33,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:33,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:33,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:33,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:33,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +28: [2022-12-02 10:52:33,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +41: [2022-12-02 10:52:33,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +28: [2022-12-02 10:52:33,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:33,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +35: [2022-12-02 10:52:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:33,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:33,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:33,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:33,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:34,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +45: [2022-12-02 10:52:34,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:34,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +45: [2022-12-02 10:52:34,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:34,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:34,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:34,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:34,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +32: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +41: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +63: [2022-12-02 10:52:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +50: [2022-12-02 10:52:34,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +21: [2022-12-02 10:52:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +50: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +21: [2022-12-02 10:52:34,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +33: [2022-12-02 10:52:34,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +59: [2022-12-02 10:52:34,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +33: [2022-12-02 10:52:34,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:34,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +32: [2022-12-02 10:52:34,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +59: [2022-12-02 10:52:34,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +58: [2022-12-02 10:52:34,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +58: [2022-12-02 10:52:34,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +58: [2022-12-02 10:52:34,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:34,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +33: [2022-12-02 10:52:34,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:34,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +48: [2022-12-02 10:52:34,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +35: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +61: [2022-12-02 10:52:34,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +63: [2022-12-02 10:52:34,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +48: [2022-12-02 10:52:34,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +33: [2022-12-02 10:52:34,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +35: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:34,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:34,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +41: [2022-12-02 10:52:34,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +41: [2022-12-02 10:52:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:34,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +41: [2022-12-02 10:52:34,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +63: [2022-12-02 10:52:34,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:34,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +54: [2022-12-02 10:52:34,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +17: [2022-12-02 10:52:34,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +17: [2022-12-02 10:52:34,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:34,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +39: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +17: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +63: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +17: [2022-12-02 10:52:34,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +33: [2022-12-02 10:52:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +45: [2022-12-02 10:52:34,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +45: [2022-12-02 10:52:34,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:34,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:34,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +40: [2022-12-02 10:52:34,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +44: [2022-12-02 10:52:34,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +11: [2022-12-02 10:52:34,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +11: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +11: [2022-12-02 10:52:34,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:34,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:34,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +51: [2022-12-02 10:52:34,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +12: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +16: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +11: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +57: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +11: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +61: [2022-12-02 10:52:34,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +24: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:34,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +38: [2022-12-02 10:52:34,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +57: [2022-12-02 10:52:34,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:34,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +61: [2022-12-02 10:52:34,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +16: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +56: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +16: [2022-12-02 10:52:34,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +57: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +57: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +16: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +62: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +46: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +38: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +44: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +38: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +47: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +47: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +46: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +34: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +47: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +24: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +46: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +34: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +52: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +10: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +47: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +47: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +10: [2022-12-02 10:52:34,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +43: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +43: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:34,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +39: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +42: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +43: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +42: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +44: [2022-12-02 10:52:34,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +20: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +37: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +37: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:34,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +37: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +20: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +37: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +36: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +20: [2022-12-02 10:52:34,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +44: [2022-12-02 10:52:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +44: [2022-12-02 10:52:34,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +10: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +54: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +46: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +38: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +56: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +24: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +24: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +56: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +31: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +24: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +52: [2022-12-02 10:52:34,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +31: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +56: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +56: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +52: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +52: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +17: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +52: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +46: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +46: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +31: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:34,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:34,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:34,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +38: [2022-12-02 10:52:34,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +20: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +36: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +36: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +20: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +36: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +36: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +53: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +20: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +53: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +53: [2022-12-02 10:52:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +53: [2022-12-02 10:52:34,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +54: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +10: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:34,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +10: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +54: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +54: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +20: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +60: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +60: [2022-12-02 10:52:34,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +60: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +20: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +20: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +55: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +22: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +60: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +60: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +30: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +60: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +22: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +55: [2022-12-02 10:52:34,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +17: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +39: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +62: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +17: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +55: [2022-12-02 10:52:34,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +55: [2022-12-02 10:52:34,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:34,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +55: [2022-12-02 10:52:34,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +60: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +22: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +22: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +62: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +62: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +62: [2022-12-02 10:52:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +62: [2022-12-02 10:52:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +60: [2022-12-02 10:52:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +62: [2022-12-02 10:52:34,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +14: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:34,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +15: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +60: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:34,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +60: [2022-12-02 10:52:34,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +39: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +28: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +39: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +18: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +42: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +23: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +40: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +14: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +61: [2022-12-02 10:52:34,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +30: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +30: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +30: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +14: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +18: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +42: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +15: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +40: [2022-12-02 10:52:34,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +61: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +15: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +61: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +47: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +61: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +42: [2022-12-02 10:52:34,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +47: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +23: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +47: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +23: [2022-12-02 10:52:34,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +47: [2022-12-02 10:52:34,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +29: [2022-12-02 10:52:34,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +54: [2022-12-02 10:52:34,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +29: [2022-12-02 10:52:34,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:34,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:34,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +42: [2022-12-02 10:52:34,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +28: [2022-12-02 10:52:34,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:34,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:34,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +54: [2022-12-02 10:52:34,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +28: [2022-12-02 10:52:34,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:34,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +28: [2022-12-02 10:52:34,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +54: [2022-12-02 10:52:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +51: [2022-12-02 10:52:34,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +13: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +13: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +17: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +54: [2022-12-02 10:52:34,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +29: [2022-12-02 10:52:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +62: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +17: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +62: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +29: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +29: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +51: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +17: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +54: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +12: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +36: [2022-12-02 10:52:34,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +11: [2022-12-02 10:52:34,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +17: [2022-12-02 10:52:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +62: [2022-12-02 10:52:34,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +36: [2022-12-02 10:52:34,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +16: [2022-12-02 10:52:34,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +11: [2022-12-02 10:52:34,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +16: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +26: [2022-12-02 10:52:34,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +43: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +10: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +39: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +26: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +34: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +26: [2022-12-02 10:52:34,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +57: [2022-12-02 10:52:34,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +34: [2022-12-02 10:52:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +10: [2022-12-02 10:52:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +46: [2022-12-02 10:52:34,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +26: [2022-12-02 10:52:34,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:34,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +39: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +43: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +43: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +39: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +19: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +43: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +20: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +24: [2022-12-02 10:52:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +40: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +52: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +25: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +26: [2022-12-02 10:52:34,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +46: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +31: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +26: [2022-12-02 10:52:34,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +53: [2022-12-02 10:52:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:34,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +30: [2022-12-02 10:52:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +37: [2022-12-02 10:52:34,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +37: [2022-12-02 10:52:34,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +49: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +53: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +53: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +53: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +53: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +11: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +11: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +52: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +22: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +52: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +52: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +55: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +55: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +55: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +51: [2022-12-02 10:52:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +60: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +60: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +46: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +19: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +46: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +46: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +10: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +51: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +25: [2022-12-02 10:52:34,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +12: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +12: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +55: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +51: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +55: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +22: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +22: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +60: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +27: [2022-12-02 10:52:34,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +49: [2022-12-02 10:52:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +27: [2022-12-02 10:52:34,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:34,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:34,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +51: [2022-12-02 10:52:34,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +51: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +21: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +49: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +21: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +21: [2022-12-02 10:52:34,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +49: [2022-12-02 10:52:34,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt... +11: [2022-12-02 10:52:34,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +43: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +14: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +16: [2022-12-02 10:52:34,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +11: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +16: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +16: [2022-12-02 10:52:34,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:34,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +57: [2022-12-02 10:52:34,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +10: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +46: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +15: [2022-12-02 10:52:34,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:34,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +34: [2022-12-02 10:52:34,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +28: [2022-12-02 10:52:34,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +46: [2022-12-02 10:52:34,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +28: [2022-12-02 10:52:34,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +34: [2022-12-02 10:52:34,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +23: [2022-12-02 10:52:34,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +31: [2022-12-02 10:52:34,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +31: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +15: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +34: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +20: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +34: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +20: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +34: [2022-12-02 10:52:34,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +60: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +52: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +60: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +60: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt... +57: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +13: [2022-12-02 10:52:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +52: [2022-12-02 10:52:34,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +52: [2022-12-02 10:52:34,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +14: [2022-12-02 10:52:34,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +60: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +18: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +23: [2022-12-02 10:52:34,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +57: [2022-12-02 10:52:34,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +57: [2022-12-02 10:52:34,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +30: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +53: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +24: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +24: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +57: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +22: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +31: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +24: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +46: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 8: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 7: [2022-12-02 10:52:34,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +53: [2022-12-02 10:52:34,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +13: [2022-12-02 10:52:34,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 1: [2022-12-02 10:52:34,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:34,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +22: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +53: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +14: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +53: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +28: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +53: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:34,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:34,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +27: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +29: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +10: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:34,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +55: [2022-12-02 10:52:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +46: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +52: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +28: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +28: [2022-12-02 10:52:34,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +52: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +52: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +20: [2022-12-02 10:52:34,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +15: [2022-12-02 10:52:34,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +18: [2022-12-02 10:52:34,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:34,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +18: [2022-12-02 10:52:34,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +13: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +25: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +14: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +14: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +18: [2022-12-02 10:52:34,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:34,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +23: [2022-12-02 10:52:34,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:34,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +58: [2022-12-02 10:52:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +19: [2022-12-02 10:52:34,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +58: [2022-12-02 10:52:34,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +29: [2022-12-02 10:52:34,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +58: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +29: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 4: [2022-12-02 10:52:34,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +58: [2022-12-02 10:52:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +30: [2022-12-02 10:52:34,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +49: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +25: [2022-12-02 10:52:34,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +30: [2022-12-02 10:52:34,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:34,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +19: [2022-12-02 10:52:34,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +19: [2022-12-02 10:52:34,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +26: [2022-12-02 10:52:34,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +29: [2022-12-02 10:52:34,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +13: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +13: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +50: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +26: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +58: [2022-12-02 10:52:34,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +25: [2022-12-02 10:52:34,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +49: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_28-model_00-model_states.pt. +21: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +21: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 9: [2022-12-02 10:52:34,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +29: [2022-12-02 10:52:34,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:34,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:34,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +28: [2022-12-02 10:52:34,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. +50: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_09-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:34,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +19: [2022-12-02 10:52:34,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:34,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:34,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +25: [2022-12-02 10:52:34,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +19: [2022-12-02 10:52:34,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +19: [2022-12-02 10:52:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:34,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +21: [2022-12-02 10:52:34,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +21: [2022-12-02 10:52:34,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +21: [2022-12-02 10:52:34,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. + 5: [2022-12-02 10:52:34,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:34,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +48: [2022-12-02 10:52:34,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:34,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +59: [2022-12-02 10:52:34,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +33: [2022-12-02 10:52:34,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:34,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +59: [2022-12-02 10:52:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:34,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:34,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:34,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:34,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +38: [2022-12-02 10:52:34,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:34,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:34,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +38: [2022-12-02 10:52:34,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:34,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +45: [2022-12-02 10:52:34,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +63: [2022-12-02 10:52:34,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +39: [2022-12-02 10:52:34,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +32: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +12: [2022-12-02 10:52:34,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +62: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +12: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +63: [2022-12-02 10:52:34,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +12: [2022-12-02 10:52:34,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +33: [2022-12-02 10:52:34,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +63: [2022-12-02 10:52:34,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:34,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +62: [2022-12-02 10:52:34,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +33: [2022-12-02 10:52:34,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:34,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:34,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:34,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +12: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +53: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +12: [2022-12-02 10:52:34,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +56: [2022-12-02 10:52:34,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:34,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:34,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:34,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +62: [2022-12-02 10:52:34,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +41: [2022-12-02 10:52:34,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:34,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:34,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +35: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +45: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +32: [2022-12-02 10:52:34,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:34,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +61: [2022-12-02 10:52:34,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:34,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:34,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +47: [2022-12-02 10:52:34,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +35: [2022-12-02 10:52:34,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:34,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:34,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:34,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:34,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +41: [2022-12-02 10:52:34,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:34,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:34,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:34,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:34,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:34,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:34,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:34,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:34,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:34,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:34,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:34,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:34,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:34,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +46: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +55: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +36: [2022-12-02 10:52:34,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +34: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +36: [2022-12-02 10:52:34,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +42: [2022-12-02 10:52:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +44: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:34,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +42: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +61: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:34,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:34,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +37: [2022-12-02 10:52:34,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +57: [2022-12-02 10:52:34,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +56: [2022-12-02 10:52:34,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:34,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:34,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:34,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +56: [2022-12-02 10:52:34,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:34,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:34,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +57: [2022-12-02 10:52:34,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +57: [2022-12-02 10:52:34,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +57: [2022-12-02 10:52:34,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:34,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +58: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +58: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +44: [2022-12-02 10:52:34,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +43: [2022-12-02 10:52:34,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +40: [2022-12-02 10:52:34,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +47: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +54: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +12: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +49: [2022-12-02 10:52:34,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +49: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +43: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +51: [2022-12-02 10:52:34,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +50: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +12: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +47: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +12: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +43: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +46: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +60: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +12: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +12: [2022-12-02 10:52:34,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +39: [2022-12-02 10:52:34,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:34,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +39: [2022-12-02 10:52:34,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:34,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +55: [2022-12-02 10:52:34,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +30: [2022-12-02 10:52:34,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +55: [2022-12-02 10:52:34,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +20: [2022-12-02 10:52:34,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +55: [2022-12-02 10:52:34,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:34,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:34,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +30: [2022-12-02 10:52:34,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:34,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +43: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +43: [2022-12-02 10:52:34,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:34,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:34,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:34,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:34,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:34,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +30: [2022-12-02 10:52:34,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +36: [2022-12-02 10:52:34,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:34,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +20: [2022-12-02 10:52:34,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +39: [2022-12-02 10:52:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +39: [2022-12-02 10:52:34,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:34,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +20: [2022-12-02 10:52:34,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +20: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +12: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +52: [2022-12-02 10:52:34,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:34,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +20: [2022-12-02 10:52:34,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:34,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +39: [2022-12-02 10:52:34,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +30: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +12: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +39: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +30: [2022-12-02 10:52:34,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:34,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +30: [2022-12-02 10:52:34,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +43: [2022-12-02 10:52:34,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:34,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +12: [2022-12-02 10:52:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +43: [2022-12-02 10:52:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +53: [2022-12-02 10:52:34,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +12: [2022-12-02 10:52:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +43: [2022-12-02 10:52:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:34,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 0: [2022-12-02 10:52:34,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +52: [2022-12-02 10:52:34,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 0: [2022-12-02 10:52:34,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:34,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:34,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +53: [2022-12-02 10:52:34,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:34,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +52: [2022-12-02 10:52:34,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +52: [2022-12-02 10:52:34,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt... +27: [2022-12-02 10:52:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +34: [2022-12-02 10:52:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +27: [2022-12-02 10:52:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +34: [2022-12-02 10:52:34,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +27: [2022-12-02 10:52:34,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:34,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:34,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:34,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:34,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +37: [2022-12-02 10:52:34,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:34,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +27: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +34: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +53: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +27: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:34,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +34: [2022-12-02 10:52:34,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +57: [2022-12-02 10:52:34,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +27: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:34,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +27: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:34,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +37: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +40: [2022-12-02 10:52:34,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +50: [2022-12-02 10:52:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:34,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +58: [2022-12-02 10:52:34,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +16: [2022-12-02 10:52:34,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +49: [2022-12-02 10:52:34,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +16: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +49: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +49: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +16: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:34,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +58: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +16: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +58: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:34,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +54: [2022-12-02 10:52:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +54: [2022-12-02 10:52:34,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +34: [2022-12-02 10:52:34,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +14: [2022-12-02 10:52:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +50: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +14: [2022-12-02 10:52:34,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +34: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +60: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +60: [2022-12-02 10:52:34,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +16: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +48: [2022-12-02 10:52:34,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +48: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:34,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +34: [2022-12-02 10:52:34,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +16: [2022-12-02 10:52:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +16: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:34,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:34,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:34,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:34,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:34,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:34,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:34,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +14: [2022-12-02 10:52:34,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:34,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:35,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +34: [2022-12-02 10:52:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +34: [2022-12-02 10:52:35,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +60: [2022-12-02 10:52:35,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +60: [2022-12-02 10:52:35,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +25: [2022-12-02 10:52:35,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +37: [2022-12-02 10:52:35,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +57: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +20: [2022-12-02 10:52:35,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:35,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +37: [2022-12-02 10:52:35,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:35,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +51: [2022-12-02 10:52:35,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +49: [2022-12-02 10:52:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +25: [2022-12-02 10:52:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:35,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +49: [2022-12-02 10:52:35,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +54: [2022-12-02 10:52:35,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +54: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +20: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +50: [2022-12-02 10:52:35,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:35,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:35,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +51: [2022-12-02 10:52:35,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +20: [2022-12-02 10:52:35,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +60: [2022-12-02 10:52:35,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:35,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +27: [2022-12-02 10:52:35,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +60: [2022-12-02 10:52:35,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +26: [2022-12-02 10:52:35,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +60: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +26: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +58: [2022-12-02 10:52:35,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +30: [2022-12-02 10:52:35,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +58: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +30: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +52: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +52: [2022-12-02 10:52:35,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_29-model_00-model_states.pt. +30: [2022-12-02 10:52:35,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +58: [2022-12-02 10:52:35,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +26: [2022-12-02 10:52:35,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:35,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +50: [2022-12-02 10:52:35,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +20: [2022-12-02 10:52:35,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +50: [2022-12-02 10:52:35,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +50: [2022-12-02 10:52:35,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +20: [2022-12-02 10:52:35,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:35,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:35,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:35,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,055] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:35,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +27: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +52: [2022-12-02 10:52:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +48: [2022-12-02 10:52:35,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +20: [2022-12-02 10:52:35,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:35,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +20: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +10: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:35,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +52: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:35,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +30: [2022-12-02 10:52:35,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:35,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:35,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +48: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +30: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +59: [2022-12-02 10:52:35,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +14: [2022-12-02 10:52:35,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +52: [2022-12-02 10:52:35,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:35,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:35,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +38: [2022-12-02 10:52:35,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +27: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +31: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +24: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:35,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +17: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +38: [2022-12-02 10:52:35,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +18: [2022-12-02 10:52:35,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:35,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +17: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +16: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:35,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +32: [2022-12-02 10:52:35,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +26: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +27: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +29: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +29: [2022-12-02 10:52:35,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:35,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +48: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +16: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +48: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +17: [2022-12-02 10:52:35,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +16: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +38: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +17: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +16: [2022-12-02 10:52:35,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:35,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +18: [2022-12-02 10:52:35,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +17: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +45: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +18: [2022-12-02 10:52:35,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +17: [2022-12-02 10:52:35,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +11: [2022-12-02 10:52:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +38: [2022-12-02 10:52:35,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +13: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +38: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +38: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +13: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +14: [2022-12-02 10:52:35,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +48: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +29: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +32: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +29: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +45: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +29: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +45: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +29: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +14: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:35,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:35,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +32: [2022-12-02 10:52:35,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +14: [2022-12-02 10:52:35,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:35,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +25: [2022-12-02 10:52:35,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +45: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +22: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +13: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +28: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +22: [2022-12-02 10:52:35,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:35,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:35,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +25: [2022-12-02 10:52:35,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +25: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +15: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +45: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +45: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +25: [2022-12-02 10:52:35,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:35,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:35,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +19: [2022-12-02 10:52:35,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +23: [2022-12-02 10:52:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +21: [2022-12-02 10:52:35,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +26: [2022-12-02 10:52:35,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +15: [2022-12-02 10:52:35,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt... +11: [2022-12-02 10:52:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +26: [2022-12-02 10:52:35,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +10: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +33: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +33: [2022-12-02 10:52:35,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +33: [2022-12-02 10:52:35,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +59: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +11: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +59: [2022-12-02 10:52:35,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +11: [2022-12-02 10:52:35,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +59: [2022-12-02 10:52:35,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +26: [2022-12-02 10:52:35,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +23: [2022-12-02 10:52:35,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +11: [2022-12-02 10:52:35,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +38: [2022-12-02 10:52:35,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +10: [2022-12-02 10:52:35,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +10: [2022-12-02 10:52:35,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +38: [2022-12-02 10:52:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +18: [2022-12-02 10:52:35,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +28: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +29: [2022-12-02 10:52:35,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +35: [2022-12-02 10:52:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +28: [2022-12-02 10:52:35,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +22: [2022-12-02 10:52:35,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +22: [2022-12-02 10:52:35,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +59: [2022-12-02 10:52:35,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +31: [2022-12-02 10:52:35,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +59: [2022-12-02 10:52:35,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +24: [2022-12-02 10:52:35,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +59: [2022-12-02 10:52:35,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +59: [2022-12-02 10:52:35,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +21: [2022-12-02 10:52:35,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +22: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +22: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +59: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +19: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +24: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +21: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +31: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +31: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +24: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +18: [2022-12-02 10:52:35,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +62: [2022-12-02 10:52:35,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:35,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:35,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:35,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +24: [2022-12-02 10:52:35,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +19: [2022-12-02 10:52:35,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +13: [2022-12-02 10:52:35,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +19: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +15: [2022-12-02 10:52:35,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +32: [2022-12-02 10:52:35,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +31: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +21: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +45: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +18: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_10-model_00-model_states.pt. +38: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +31: [2022-12-02 10:52:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +18: [2022-12-02 10:52:35,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +13: [2022-12-02 10:52:35,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +18: [2022-12-02 10:52:35,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +38: [2022-12-02 10:52:35,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +19: [2022-12-02 10:52:35,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +29: [2022-12-02 10:52:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +22: [2022-12-02 10:52:35,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +61: [2022-12-02 10:52:35,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +22: [2022-12-02 10:52:35,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +21: [2022-12-02 10:52:35,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +61: [2022-12-02 10:52:35,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +15: [2022-12-02 10:52:35,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +21: [2022-12-02 10:52:35,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +45: [2022-12-02 10:52:35,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +33: [2022-12-02 10:52:35,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +35: [2022-12-02 10:52:35,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +62: [2022-12-02 10:52:35,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +62: [2022-12-02 10:52:35,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +35: [2022-12-02 10:52:35,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:35,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:35,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:35,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +47: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:35,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:35,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +55: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +50: [2022-12-02 10:52:35,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +55: [2022-12-02 10:52:35,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +53: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +40: [2022-12-02 10:52:35,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +61: [2022-12-02 10:52:35,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:35,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:35,443] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +58: [2022-12-02 10:52:35,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +58: [2022-12-02 10:52:35,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +54: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +48: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,451] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +41: [2022-12-02 10:52:35,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +41: [2022-12-02 10:52:35,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +49: [2022-12-02 10:52:35,463] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +56: [2022-12-02 10:52:35,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +37: [2022-12-02 10:52:35,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +36: [2022-12-02 10:52:35,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +51: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +39: [2022-12-02 10:52:35,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +46: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +34: [2022-12-02 10:52:35,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +63: [2022-12-02 10:52:35,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +57: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +60: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +42: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +44: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +52: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt... +43: [2022-12-02 10:52:35,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +56: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +47: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +36: [2022-12-02 10:52:35,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +63: [2022-12-02 10:52:35,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +53: [2022-12-02 10:52:35,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +42: [2022-12-02 10:52:35,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +46: [2022-12-02 10:52:35,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +44: [2022-12-02 10:52:35,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:35,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +34: [2022-12-02 10:52:35,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +39: [2022-12-02 10:52:35,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:35,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +38: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:35,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:35,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +43: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:35,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:35,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +58: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:35,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:35,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +40: [2022-12-02 10:52:35,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:35,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:35,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +49: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +50: [2022-12-02 10:52:35,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:35,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:35,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +32: [2022-12-02 10:52:35,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:35,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:35,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +51: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +37: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +45: [2022-12-02 10:52:35,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +57: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +52: [2022-12-02 10:52:35,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +60: [2022-12-02 10:52:35,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +48: [2022-12-02 10:52:35,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:35,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_30-model_00-model_states.pt. +54: [2022-12-02 10:52:35,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:35,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:35,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:35,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:35,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:35,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:35,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:35,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:35,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +59: [2022-12-02 10:52:35,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:35,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:35,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:35,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:35,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:35,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:35,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:35,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:35,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:35,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:35,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:35,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:35,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +12: [2022-12-02 10:52:35,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +38: [2022-12-02 10:52:35,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:35,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +12: [2022-12-02 10:52:35,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:35,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:35,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:35,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:35,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +17: [2022-12-02 10:52:35,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +32: [2022-12-02 10:52:35,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +17: [2022-12-02 10:52:35,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +45: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:35,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +11: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +62: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +11: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +45: [2022-12-02 10:52:35,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +17: [2022-12-02 10:52:35,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +62: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +33: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +62: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +11: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +33: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:35,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:35,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +23: [2022-12-02 10:52:35,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +32: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +20: [2022-12-02 10:52:35,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +19: [2022-12-02 10:52:35,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +23: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +23: [2022-12-02 10:52:35,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +35: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +35: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +30: [2022-12-02 10:52:35,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +19: [2022-12-02 10:52:35,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +33: [2022-12-02 10:52:35,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +30: [2022-12-02 10:52:35,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +45: [2022-12-02 10:52:35,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +12: [2022-12-02 10:52:35,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +45: [2022-12-02 10:52:35,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:35,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +33: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +33: [2022-12-02 10:52:35,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +33: [2022-12-02 10:52:35,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:35,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +33: [2022-12-02 10:52:35,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +12: [2022-12-02 10:52:35,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +62: [2022-12-02 10:52:35,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +29: [2022-12-02 10:52:35,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +61: [2022-12-02 10:52:35,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +11: [2022-12-02 10:52:35,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +17: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +61: [2022-12-02 10:52:35,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +62: [2022-12-02 10:52:35,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +23: [2022-12-02 10:52:35,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:35,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +62: [2022-12-02 10:52:35,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +62: [2022-12-02 10:52:35,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +14: [2022-12-02 10:52:35,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +25: [2022-12-02 10:52:35,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +25: [2022-12-02 10:52:35,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +12: [2022-12-02 10:52:35,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +12: [2022-12-02 10:52:35,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:35,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:35,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:35,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:35,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:35,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:35,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +35: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +10: [2022-12-02 10:52:35,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +27: [2022-12-02 10:52:35,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +35: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +35: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +35: [2022-12-02 10:52:35,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +17: [2022-12-02 10:52:35,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:35,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +35: [2022-12-02 10:52:35,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +24: [2022-12-02 10:52:35,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:35,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +17: [2022-12-02 10:52:35,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +11: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +20: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +31: [2022-12-02 10:52:35,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:35,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +11: [2022-12-02 10:52:35,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:35,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +55: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +14: [2022-12-02 10:52:35,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +24: [2022-12-02 10:52:35,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +24: [2022-12-02 10:52:35,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +62: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +30: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +55: [2022-12-02 10:52:35,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +14: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +14: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +21: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +21: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +62: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +21: [2022-12-02 10:52:35,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +62: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +23: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +23: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +55: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +62: [2022-12-02 10:52:35,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +10: [2022-12-02 10:52:35,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +61: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 4: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +23: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 6: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +23: [2022-12-02 10:52:35,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:35,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:35,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:35,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 8: [2022-12-02 10:52:35,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +20: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:35,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +10: [2022-12-02 10:52:35,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:35,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:35,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +10: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +13: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +27: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +19: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +26: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +16: [2022-12-02 10:52:35,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +35: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +29: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +29: [2022-12-02 10:52:35,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:35,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +35: [2022-12-02 10:52:35,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:35,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +19: [2022-12-02 10:52:35,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +19: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 1: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 3: [2022-12-02 10:52:35,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +16: [2022-12-02 10:52:35,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +16: [2022-12-02 10:52:35,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +16: [2022-12-02 10:52:35,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:35,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +25: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 0: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 0: [2022-12-02 10:52:35,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:35,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +15: [2022-12-02 10:52:35,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +15: [2022-12-02 10:52:35,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +30: [2022-12-02 10:52:35,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:35,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:35,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +30: [2022-12-02 10:52:35,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +61: [2022-12-02 10:52:35,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +30: [2022-12-02 10:52:35,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:35,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:35,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +39: [2022-12-02 10:52:35,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +29: [2022-12-02 10:52:35,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:35,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +39: [2022-12-02 10:52:35,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +29: [2022-12-02 10:52:35,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +41: [2022-12-02 10:52:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +39: [2022-12-02 10:52:35,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:35,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +31: [2022-12-02 10:52:35,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +47: [2022-12-02 10:52:35,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +25: [2022-12-02 10:52:35,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +39: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +24: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +47: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +24: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +39: [2022-12-02 10:52:35,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +29: [2022-12-02 10:52:35,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:35,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:35,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +29: [2022-12-02 10:52:35,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:35,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +47: [2022-12-02 10:52:35,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +25: [2022-12-02 10:52:35,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +47: [2022-12-02 10:52:35,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +24: [2022-12-02 10:52:35,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +41: [2022-12-02 10:52:35,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +41: [2022-12-02 10:52:35,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +18: [2022-12-02 10:52:35,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +41: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +25: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:35,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +21: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +55: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +21: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +41: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +55: [2022-12-02 10:52:35,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +25: [2022-12-02 10:52:35,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:35,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +25: [2022-12-02 10:52:35,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +47: [2022-12-02 10:52:35,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +21: [2022-12-02 10:52:35,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +47: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +47: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +13: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +47: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +24: [2022-12-02 10:52:35,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +46: [2022-12-02 10:52:35,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +28: [2022-12-02 10:52:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +28: [2022-12-02 10:52:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +21: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:35,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:35,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:35,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +61: [2022-12-02 10:52:35,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:35,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +28: [2022-12-02 10:52:35,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:35,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +22: [2022-12-02 10:52:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +61: [2022-12-02 10:52:35,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +61: [2022-12-02 10:52:35,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:35,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +46: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +22: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +26: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +61: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +22: [2022-12-02 10:52:35,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt... +18: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +61: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +18: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +13: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +34: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +13: [2022-12-02 10:52:35,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +34: [2022-12-02 10:52:35,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +13: [2022-12-02 10:52:35,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +26: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 9: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +18: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +31: [2022-12-02 10:52:35,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +46: [2022-12-02 10:52:35,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +24: [2022-12-02 10:52:35,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:35,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +16: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +16: [2022-12-02 10:52:35,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +24: [2022-12-02 10:52:35,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:35,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +36: [2022-12-02 10:52:35,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +55: [2022-12-02 10:52:35,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:35,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 2: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:35,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +31: [2022-12-02 10:52:35,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:35,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +36: [2022-12-02 10:52:35,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +15: [2022-12-02 10:52:35,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +26: [2022-12-02 10:52:35,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +55: [2022-12-02 10:52:35,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +15: [2022-12-02 10:52:35,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +15: [2022-12-02 10:52:35,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +21: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +55: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +21: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:35,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. + 7: [2022-12-02 10:52:35,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +55: [2022-12-02 10:52:35,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +18: [2022-12-02 10:52:35,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:35,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:35,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +28: [2022-12-02 10:52:35,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +36: [2022-12-02 10:52:35,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +36: [2022-12-02 10:52:35,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:35,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +39: [2022-12-02 10:52:35,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +47: [2022-12-02 10:52:35,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +18: [2022-12-02 10:52:35,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:35,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:35,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 5: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +26: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:35,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:35,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +63: [2022-12-02 10:52:35,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +13: [2022-12-02 10:52:35,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:35,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +41: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:35,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:35,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +16: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +44: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +16: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:35,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:35,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +15: [2022-12-02 10:52:35,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:35,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +63: [2022-12-02 10:52:35,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +15: [2022-12-02 10:52:35,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +58: [2022-12-02 10:52:35,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +58: [2022-12-02 10:52:35,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +15: [2022-12-02 10:52:35,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +58: [2022-12-02 10:52:35,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +58: [2022-12-02 10:52:35,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:35,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:35,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +58: [2022-12-02 10:52:35,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:35,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +44: [2022-12-02 10:52:35,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +15: [2022-12-02 10:52:35,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +56: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +39: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:35,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:35,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +15: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +15: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +42: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +15: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +56: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:35,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:35,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:35,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:35,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:35,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:35,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +40: [2022-12-02 10:52:35,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:35,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:35,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:35,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:35,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:35,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:35,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:35,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +22: [2022-12-02 10:52:36,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:36,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:36,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:36,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +46: [2022-12-02 10:52:36,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +22: [2022-12-02 10:52:36,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:36,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:36,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +22: [2022-12-02 10:52:36,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_11-model_00-model_states.pt. +36: [2022-12-02 10:52:36,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:36,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,010] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:36,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:36,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:36,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:36,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +41: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:36,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:36,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:36,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +57: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +50: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:36,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +46: [2022-12-02 10:52:36,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +38: [2022-12-02 10:52:36,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +39: [2022-12-02 10:52:36,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +54: [2022-12-02 10:52:36,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:36,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:36,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +32: [2022-12-02 10:52:36,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +22: [2022-12-02 10:52:36,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +22: [2022-12-02 10:52:36,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +36: [2022-12-02 10:52:36,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +22: [2022-12-02 10:52:36,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +47: [2022-12-02 10:52:36,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:36,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +53: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +53: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:36,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:36,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +47: [2022-12-02 10:52:36,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +45: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +49: [2022-12-02 10:52:36,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +22: [2022-12-02 10:52:36,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +58: [2022-12-02 10:52:36,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +58: [2022-12-02 10:52:36,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:36,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:36,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:36,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +36: [2022-12-02 10:52:36,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +34: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +34: [2022-12-02 10:52:36,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:36,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:36,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +56: [2022-12-02 10:52:36,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:36,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +51: [2022-12-02 10:52:36,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:36,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:36,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +46: [2022-12-02 10:52:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:36,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:36,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:36,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +33: [2022-12-02 10:52:36,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:36,066] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +42: [2022-12-02 10:52:36,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:36,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:36,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:36,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:36,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +56: [2022-12-02 10:52:36,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:36,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:36,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +33: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:36,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:36,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +43: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +37: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:36,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +52: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +58: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +48: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:36,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:36,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:36,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +48: [2022-12-02 10:52:36,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +44: [2022-12-02 10:52:36,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +60: [2022-12-02 10:52:36,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt... +63: [2022-12-02 10:52:36,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:36,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:36,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:36,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +58: [2022-12-02 10:52:36,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +58: [2022-12-02 10:52:36,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +63: [2022-12-02 10:52:36,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:36,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:36,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:36,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:36,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:36,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +40: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:36,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +48: [2022-12-02 10:52:36,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:36,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:36,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +50: [2022-12-02 10:52:36,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,135] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +44: [2022-12-02 10:52:36,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:36,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:36,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +57: [2022-12-02 10:52:36,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:36,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +50: [2022-12-02 10:52:36,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +59: [2022-12-02 10:52:36,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +38: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:36,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +43: [2022-12-02 10:52:36,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +45: [2022-12-02 10:52:36,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +51: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +62: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +52: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +49: [2022-12-02 10:52:36,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +37: [2022-12-02 10:52:36,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +53: [2022-12-02 10:52:36,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +54: [2022-12-02 10:52:36,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +32: [2022-12-02 10:52:36,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:36,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:36,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +60: [2022-12-02 10:52:36,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_31-model_00-model_states.pt. +32: [2022-12-02 10:52:36,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:36,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +61: [2022-12-02 10:52:36,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +61: [2022-12-02 10:52:36,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +61: [2022-12-02 10:52:36,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +61: [2022-12-02 10:52:36,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +61: [2022-12-02 10:52:36,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +62: [2022-12-02 10:52:36,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +12: [2022-12-02 10:52:36,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +62: [2022-12-02 10:52:36,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +12: [2022-12-02 10:52:36,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +62: [2022-12-02 10:52:36,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +12: [2022-12-02 10:52:36,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +62: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +39: [2022-12-02 10:52:36,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +61: [2022-12-02 10:52:36,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +35: [2022-12-02 10:52:36,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +35: [2022-12-02 10:52:36,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +47: [2022-12-02 10:52:36,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +61: [2022-12-02 10:52:36,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +30: [2022-12-02 10:52:36,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +39: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +30: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +12: [2022-12-02 10:52:36,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +20: [2022-12-02 10:52:36,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:36,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +25: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +25: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +55: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:36,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +23: [2022-12-02 10:52:36,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +39: [2022-12-02 10:52:36,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +27: [2022-12-02 10:52:36,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:36,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +27: [2022-12-02 10:52:36,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:36,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +23: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +41: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +41: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +55: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +41: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +55: [2022-12-02 10:52:36,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:36,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +39: [2022-12-02 10:52:36,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:36,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:36,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:36,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +61: [2022-12-02 10:52:36,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +10: [2022-12-02 10:52:36,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +47: [2022-12-02 10:52:36,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +12: [2022-12-02 10:52:36,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +47: [2022-12-02 10:52:36,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +12: [2022-12-02 10:52:36,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:36,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +12: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +61: [2022-12-02 10:52:36,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +12: [2022-12-02 10:52:36,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +61: [2022-12-02 10:52:36,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +12: [2022-12-02 10:52:36,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:36,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +39: [2022-12-02 10:52:36,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +10: [2022-12-02 10:52:36,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +14: [2022-12-02 10:52:36,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +34: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +24: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +34: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +24: [2022-12-02 10:52:36,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +34: [2022-12-02 10:52:36,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +31: [2022-12-02 10:52:36,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +24: [2022-12-02 10:52:36,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:36,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:36,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:36,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +24: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +31: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +24: [2022-12-02 10:52:36,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:36,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:36,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +39: [2022-12-02 10:52:36,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +14: [2022-12-02 10:52:36,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +47: [2022-12-02 10:52:36,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +30: [2022-12-02 10:52:36,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +47: [2022-12-02 10:52:36,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +47: [2022-12-02 10:52:36,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +20: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +36: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +25: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +40: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +17: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +40: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +25: [2022-12-02 10:52:36,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +40: [2022-12-02 10:52:36,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +20: [2022-12-02 10:52:36,473] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +63: [2022-12-02 10:52:36,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +25: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +36: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +25: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +39: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +17: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +63: [2022-12-02 10:52:36,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +39: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +27: [2022-12-02 10:52:36,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +46: [2022-12-02 10:52:36,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +27: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +46: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +39: [2022-12-02 10:52:36,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +27: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +44: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +17: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +44: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +20: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +20: [2022-12-02 10:52:36,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +63: [2022-12-02 10:52:36,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +41: [2022-12-02 10:52:36,489] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +21: [2022-12-02 10:52:36,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +36: [2022-12-02 10:52:36,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +41: [2022-12-02 10:52:36,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +30: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +44: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +44: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +30: [2022-12-02 10:52:36,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:36,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +21: [2022-12-02 10:52:36,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +59: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +59: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +20: [2022-12-02 10:52:36,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +47: [2022-12-02 10:52:36,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +20: [2022-12-02 10:52:36,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:36,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +25: [2022-12-02 10:52:36,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:36,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:36,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +27: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +47: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +10: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:36,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +47: [2022-12-02 10:52:36,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +47: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +27: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +42: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +25: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +19: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +42: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +11: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +11: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +10: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +25: [2022-12-02 10:52:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:36,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +10: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +42: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +17: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +24: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +31: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +17: [2022-12-02 10:52:36,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +23: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +34: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +19: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:36,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:36,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +19: [2022-12-02 10:52:36,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 4: [2022-12-02 10:52:36,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:36,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:36,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 4: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +53: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +23: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +34: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +24: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +24: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +41: [2022-12-02 10:52:36,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +24: [2022-12-02 10:52:36,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +50: [2022-12-02 10:52:36,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +31: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +31: [2022-12-02 10:52:36,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +23: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +34: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +20: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:36,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:36,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:36,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:36,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +20: [2022-12-02 10:52:36,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:36,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +20: [2022-12-02 10:52:36,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:36,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +30: [2022-12-02 10:52:36,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +23: [2022-12-02 10:52:36,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +56: [2022-12-02 10:52:36,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +41: [2022-12-02 10:52:36,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:36,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +53: [2022-12-02 10:52:36,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +30: [2022-12-02 10:52:36,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +30: [2022-12-02 10:52:36,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +50: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +30: [2022-12-02 10:52:36,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +50: [2022-12-02 10:52:36,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +27: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +27: [2022-12-02 10:52:36,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +30: [2022-12-02 10:52:36,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +63: [2022-12-02 10:52:36,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +27: [2022-12-02 10:52:36,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:36,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +27: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +10: [2022-12-02 10:52:36,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +57: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +10: [2022-12-02 10:52:36,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +56: [2022-12-02 10:52:36,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +10: [2022-12-02 10:52:36,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:36,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:36,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +31: [2022-12-02 10:52:36,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +57: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +56: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +56: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +56: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +24: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +31: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +57: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +49: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +31: [2022-12-02 10:52:36,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +45: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +14: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +14: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +57: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +24: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +24: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +63: [2022-12-02 10:52:36,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +57: [2022-12-02 10:52:36,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +45: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +46: [2022-12-02 10:52:36,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +63: [2022-12-02 10:52:36,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +34: [2022-12-02 10:52:36,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +63: [2022-12-02 10:52:36,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +24: [2022-12-02 10:52:36,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +34: [2022-12-02 10:52:36,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +21: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +24: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +43: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +24: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:36,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:36,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +51: [2022-12-02 10:52:36,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +31: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +43: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +45: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +43: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +36: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +59: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +45: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +45: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +32: [2022-12-02 10:52:36,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +54: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +34: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +14: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +14: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +29: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +29: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +21: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +21: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +38: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +32: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +14: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +34: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +14: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +34: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +36: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:36,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +58: [2022-12-02 10:52:36,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +14: [2022-12-02 10:52:36,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +58: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +21: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +44: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +48: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +11: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +44: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +15: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +46: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +15: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +38: [2022-12-02 10:52:36,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +15: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +48: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +48: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +60: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +38: [2022-12-02 10:52:36,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +52: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +52: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +40: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +40: [2022-12-02 10:52:36,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +40: [2022-12-02 10:52:36,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +11: [2022-12-02 10:52:36,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +11: [2022-12-02 10:52:36,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +40: [2022-12-02 10:52:36,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +11: [2022-12-02 10:52:36,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +40: [2022-12-02 10:52:36,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +19: [2022-12-02 10:52:36,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +42: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +40: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +60: [2022-12-02 10:52:36,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +63: [2022-12-02 10:52:36,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +21: [2022-12-02 10:52:36,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:36,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +40: [2022-12-02 10:52:36,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +63: [2022-12-02 10:52:36,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +21: [2022-12-02 10:52:36,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:36,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:36,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +63: [2022-12-02 10:52:36,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +42: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +42: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +63: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +19: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +19: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +19: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +19: [2022-12-02 10:52:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +33: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +16: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +21: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +33: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +46: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +60: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +26: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:36,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +46: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +60: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +46: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +22: [2022-12-02 10:52:36,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +46: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +46: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +13: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +50: [2022-12-02 10:52:36,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:36,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +53: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +18: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +53: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +53: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +59: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:36,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +56: [2022-12-02 10:52:36,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +26: [2022-12-02 10:52:36,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +26: [2022-12-02 10:52:36,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +59: [2022-12-02 10:52:36,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +16: [2022-12-02 10:52:36,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 6: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +50: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +28: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +50: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +11: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +29: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +33: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +18: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +11: [2022-12-02 10:52:36,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +16: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +21: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +21: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +16: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +52: [2022-12-02 10:52:36,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +59: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +59: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +59: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:36,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +33: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +37: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +22: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... + 6: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +15: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +22: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +29: [2022-12-02 10:52:36,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +56: [2022-12-02 10:52:36,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +13: [2022-12-02 10:52:36,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +29: [2022-12-02 10:52:36,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:36,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +49: [2022-12-02 10:52:36,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +13: [2022-12-02 10:52:36,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:36,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +44: [2022-12-02 10:52:36,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:36,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +15: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +28: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +28: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +18: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +13: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt... +49: [2022-12-02 10:52:36,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +36: [2022-12-02 10:52:36,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +36: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +11: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt... +15: [2022-12-02 10:52:36,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:36,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:36,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +44: [2022-12-02 10:52:36,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:36,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +15: [2022-12-02 10:52:36,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:36,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:36,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +36: [2022-12-02 10:52:36,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +19: [2022-12-02 10:52:36,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +36: [2022-12-02 10:52:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +11: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +36: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +11: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +62: [2022-12-02 10:52:36,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:36,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +11: [2022-12-02 10:52:36,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +57: [2022-12-02 10:52:36,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +28: [2022-12-02 10:52:36,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +42: [2022-12-02 10:52:36,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +62: [2022-12-02 10:52:36,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +54: [2022-12-02 10:52:36,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +19: [2022-12-02 10:52:36,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +19: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +50: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +57: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +43: [2022-12-02 10:52:36,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:36,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +45: [2022-12-02 10:52:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +50: [2022-12-02 10:52:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:36,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +53: [2022-12-02 10:52:36,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:36,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 8: [2022-12-02 10:52:36,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +53: [2022-12-02 10:52:36,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +51: [2022-12-02 10:52:36,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 0: [2022-12-02 10:52:36,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +50: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +58: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 8: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +53: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +54: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +58: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:36,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +28: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +58: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +28: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +32: [2022-12-02 10:52:36,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +50: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +53: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +53: [2022-12-02 10:52:36,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +50: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +45: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 3: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:36,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:36,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:36,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 3: [2022-12-02 10:52:36,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:36,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +28: [2022-12-02 10:52:36,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +38: [2022-12-02 10:52:36,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:36,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +38: [2022-12-02 10:52:36,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:36,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +52: [2022-12-02 10:52:36,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +49: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +52: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +52: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +52: [2022-12-02 10:52:36,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +28: [2022-12-02 10:52:36,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:36,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +43: [2022-12-02 10:52:36,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +56: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +48: [2022-12-02 10:52:36,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:36,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:36,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:36,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +56: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +56: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:36,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:36,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:36,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +57: [2022-12-02 10:52:36,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +57: [2022-12-02 10:52:36,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:36,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:36,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 7: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:36,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:36,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +32: [2022-12-02 10:52:36,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:36,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +58: [2022-12-02 10:52:36,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:36,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:36,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +16: [2022-12-02 10:52:36,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +43: [2022-12-02 10:52:36,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:36,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +43: [2022-12-02 10:52:36,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:36,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:36,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +16: [2022-12-02 10:52:36,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +58: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +16: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +16: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +16: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +33: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +60: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +58: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 2: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +58: [2022-12-02 10:52:36,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +58: [2022-12-02 10:52:36,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +16: [2022-12-02 10:52:36,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +51: [2022-12-02 10:52:36,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +26: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +33: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +33: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +58: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +61: [2022-12-02 10:52:36,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 1: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +26: [2022-12-02 10:52:36,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +32: [2022-12-02 10:52:36,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +22: [2022-12-02 10:52:36,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +22: [2022-12-02 10:52:36,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:36,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:36,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +61: [2022-12-02 10:52:36,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:36,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +26: [2022-12-02 10:52:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +26: [2022-12-02 10:52:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +37: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +37: [2022-12-02 10:52:36,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 5: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +18: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +52: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:36,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +13: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +45: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +13: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. +45: [2022-12-02 10:52:36,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 5: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_12-model_00-model_states.pt. + 9: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +61: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +38: [2022-12-02 10:52:36,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:36,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:36,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:36,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:36,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:36,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:36,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:36,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:36,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +32: [2022-12-02 10:52:36,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:36,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:36,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_32-model_00-model_states.pt. +32: [2022-12-02 10:52:36,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +13: [2022-12-02 10:52:36,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +32: [2022-12-02 10:52:36,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:36,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +13: [2022-12-02 10:52:36,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:36,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:36,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:36,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +16: [2022-12-02 10:52:36,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:36,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +13: [2022-12-02 10:52:36,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:36,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +16: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +16: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:36,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:36,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:36,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:36,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:36,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +22: [2022-12-02 10:52:36,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:36,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:36,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:36,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:36,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:36,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:36,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +22: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:36,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:36,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:36,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +55: [2022-12-02 10:52:36,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +55: [2022-12-02 10:52:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +26: [2022-12-02 10:52:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +55: [2022-12-02 10:52:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:36,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +22: [2022-12-02 10:52:36,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:36,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +22: [2022-12-02 10:52:36,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +18: [2022-12-02 10:52:36,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +18: [2022-12-02 10:52:36,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:36,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:36,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +18: [2022-12-02 10:52:36,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:36,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:36,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +13: [2022-12-02 10:52:36,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:36,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:36,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:36,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:36,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:36,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:36,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:36,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:36,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +61: [2022-12-02 10:52:36,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +61: [2022-12-02 10:52:36,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +55: [2022-12-02 10:52:36,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:36,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:36,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:36,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:36,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:36,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:36,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +35: [2022-12-02 10:52:36,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:36,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:36,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:36,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:36,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:36,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:36,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:36,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:36,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:36,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:36,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +35: [2022-12-02 10:52:36,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:36,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:36,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +36: [2022-12-02 10:52:36,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +47: [2022-12-02 10:52:36,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:36,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +40: [2022-12-02 10:52:36,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:36,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:36,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:36,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:36,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:36,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:37,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +63: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:37,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:37,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:37,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +41: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +40: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +39: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +39: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +34: [2022-12-02 10:52:37,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +44: [2022-12-02 10:52:37,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +63: [2022-12-02 10:52:37,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +34: [2022-12-02 10:52:37,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +47: [2022-12-02 10:52:37,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +47: [2022-12-02 10:52:37,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +41: [2022-12-02 10:52:37,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +46: [2022-12-02 10:52:37,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,058] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +41: [2022-12-02 10:52:37,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +63: [2022-12-02 10:52:37,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:37,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +41: [2022-12-02 10:52:37,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:37,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +23: [2022-12-02 10:52:37,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +36: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:37,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:37,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +53: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +60: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +48: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +58: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:37,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +58: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +58: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +58: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +58: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +53: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +58: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +50: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +48: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +23: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +50: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +50: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +50: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +49: [2022-12-02 10:52:37,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +50: [2022-12-02 10:52:37,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +57: [2022-12-02 10:52:37,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:37,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:37,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +20: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +42: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +56: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +42: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +45: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +23: [2022-12-02 10:52:37,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +20: [2022-12-02 10:52:37,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:37,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:37,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:37,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +60: [2022-12-02 10:52:37,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +46: [2022-12-02 10:52:37,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:37,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +44: [2022-12-02 10:52:37,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +10: [2022-12-02 10:52:37,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:37,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +43: [2022-12-02 10:52:37,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +20: [2022-12-02 10:52:37,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +46: [2022-12-02 10:52:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +44: [2022-12-02 10:52:37,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +46: [2022-12-02 10:52:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +20: [2022-12-02 10:52:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +30: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +21: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +45: [2022-12-02 10:52:37,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:37,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +30: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +21: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +46: [2022-12-02 10:52:37,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +30: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:37,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +30: [2022-12-02 10:52:37,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +30: [2022-12-02 10:52:37,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:37,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +30: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +54: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +17: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +42: [2022-12-02 10:52:37,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +30: [2022-12-02 10:52:37,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +30: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +43: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +30: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +43: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +30: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:37,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +30: [2022-12-02 10:52:37,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:37,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +51: [2022-12-02 10:52:37,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +53: [2022-12-02 10:52:37,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +43: [2022-12-02 10:52:37,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:37,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +54: [2022-12-02 10:52:37,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +29: [2022-12-02 10:52:37,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +59: [2022-12-02 10:52:37,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +42: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +15: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +54: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +29: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +54: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +57: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +29: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +44: [2022-12-02 10:52:37,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +29: [2022-12-02 10:52:37,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +42: [2022-12-02 10:52:37,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +29: [2022-12-02 10:52:37,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +42: [2022-12-02 10:52:37,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +33: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +15: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +42: [2022-12-02 10:52:37,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +15: [2022-12-02 10:52:37,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:37,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:37,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,167] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +17: [2022-12-02 10:52:37,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +17: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +29: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:37,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +27: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +59: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +44: [2022-12-02 10:52:37,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +27: [2022-12-02 10:52:37,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:37,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +27: [2022-12-02 10:52:37,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +27: [2022-12-02 10:52:37,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:37,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +48: [2022-12-02 10:52:37,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +58: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +17: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +58: [2022-12-02 10:52:37,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +17: [2022-12-02 10:52:37,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +37: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +12: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +59: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +12: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +45: [2022-12-02 10:52:37,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +17: [2022-12-02 10:52:37,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +58: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +17: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +58: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +49: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +59: [2022-12-02 10:52:37,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +25: [2022-12-02 10:52:37,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:37,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +49: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +25: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +50: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +25: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +50: [2022-12-02 10:52:37,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +14: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +50: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +14: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +49: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +14: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +49: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +49: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +37: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +52: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +23: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +23: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +52: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... +23: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +23: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +62: [2022-12-02 10:52:37,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +52: [2022-12-02 10:52:37,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +14: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +10: [2022-12-02 10:52:37,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:37,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:37,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:37,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +10: [2022-12-02 10:52:37,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +11: [2022-12-02 10:52:37,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +56: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +11: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +21: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +20: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +14: [2022-12-02 10:52:37,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:37,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:37,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +62: [2022-12-02 10:52:37,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +60: [2022-12-02 10:52:37,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +20: [2022-12-02 10:52:37,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +20: [2022-12-02 10:52:37,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +38: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +59: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +32: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +10: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +38: [2022-12-02 10:52:37,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +21: [2022-12-02 10:52:37,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:37,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +59: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +59: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +59: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +49: [2022-12-02 10:52:37,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +32: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +32: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +38: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +32: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:37,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +32: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +38: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +32: [2022-12-02 10:52:37,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +32: [2022-12-02 10:52:37,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +32: [2022-12-02 10:52:37,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +37: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +27: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +48: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +50: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +23: [2022-12-02 10:52:37,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +58: [2022-12-02 10:52:37,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +50: [2022-12-02 10:52:37,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +23: [2022-12-02 10:52:37,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +49: [2022-12-02 10:52:37,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +20: [2022-12-02 10:52:37,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:37,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +54: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +23: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +49: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +10: [2022-12-02 10:52:37,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:37,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +50: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +20: [2022-12-02 10:52:37,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +48: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +21: [2022-12-02 10:52:37,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:37,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +29: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +56: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +29: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +56: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +54: [2022-12-02 10:52:37,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +24: [2022-12-02 10:52:37,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:37,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +56: [2022-12-02 10:52:37,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +27: [2022-12-02 10:52:37,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +24: [2022-12-02 10:52:37,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +24: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +27: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +33: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +33: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +24: [2022-12-02 10:52:37,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +30: [2022-12-02 10:52:37,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +60: [2022-12-02 10:52:37,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +24: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +29: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +60: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +60: [2022-12-02 10:52:37,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +60: [2022-12-02 10:52:37,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +15: [2022-12-02 10:52:37,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +30: [2022-12-02 10:52:37,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:37,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +20: [2022-12-02 10:52:37,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +21: [2022-12-02 10:52:37,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:37,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:37,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +51: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +20: [2022-12-02 10:52:37,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:37,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:37,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +10: [2022-12-02 10:52:37,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +18: [2022-12-02 10:52:37,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +27: [2022-12-02 10:52:37,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +14: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +52: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +62: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +54: [2022-12-02 10:52:37,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +11: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +54: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +28: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +18: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +54: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +45: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +52: [2022-12-02 10:52:37,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +51: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +52: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_33-model_00-model_states.pt. +16: [2022-12-02 10:52:37,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +51: [2022-12-02 10:52:37,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +45: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +51: [2022-12-02 10:52:37,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +28: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +15: [2022-12-02 10:52:37,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:37,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +51: [2022-12-02 10:52:37,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +11: [2022-12-02 10:52:37,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +29: [2022-12-02 10:52:37,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +54: [2022-12-02 10:52:37,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +12: [2022-12-02 10:52:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +51: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +31: [2022-12-02 10:52:37,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +31: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +31: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +54: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +31: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +31: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +31: [2022-12-02 10:52:37,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +15: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +29: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +14: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +27: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +54: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:37,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:37,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:37,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:37,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +30: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +30: [2022-12-02 10:52:37,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +33: [2022-12-02 10:52:37,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:37,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:37,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +15: [2022-12-02 10:52:37,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:37,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +29: [2022-12-02 10:52:37,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:37,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +29: [2022-12-02 10:52:37,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:37,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +15: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +19: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +62: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +15: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +38: [2022-12-02 10:52:37,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,301] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +12: [2022-12-02 10:52:37,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +25: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +19: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +12: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +14: [2022-12-02 10:52:37,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +38: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +25: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +38: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +38: [2022-12-02 10:52:37,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +25: [2022-12-02 10:52:37,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +52: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +25: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +52: [2022-12-02 10:52:37,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +52: [2022-12-02 10:52:37,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +32: [2022-12-02 10:52:37,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +32: [2022-12-02 10:52:37,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +52: [2022-12-02 10:52:37,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +27: [2022-12-02 10:52:37,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +52: [2022-12-02 10:52:37,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +52: [2022-12-02 10:52:37,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +52: [2022-12-02 10:52:37,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +11: [2022-12-02 10:52:37,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +62: [2022-12-02 10:52:37,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +14: [2022-12-02 10:52:37,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +14: [2022-12-02 10:52:37,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +18: [2022-12-02 10:52:37,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +24: [2022-12-02 10:52:37,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +55: [2022-12-02 10:52:37,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +32: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +55: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +26: [2022-12-02 10:52:37,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +32: [2022-12-02 10:52:37,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +13: [2022-12-02 10:52:37,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +61: [2022-12-02 10:52:37,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +61: [2022-12-02 10:52:37,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +55: [2022-12-02 10:52:37,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +55: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +22: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +55: [2022-12-02 10:52:37,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:37,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:37,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +22: [2022-12-02 10:52:37,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:37,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +13: [2022-12-02 10:52:37,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:37,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +18: [2022-12-02 10:52:37,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +13: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +26: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +61: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +13: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +38: [2022-12-02 10:52:37,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +26: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +26: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +13: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +28: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +38: [2022-12-02 10:52:37,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +26: [2022-12-02 10:52:37,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +26: [2022-12-02 10:52:37,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:37,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:37,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:37,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +16: [2022-12-02 10:52:37,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +35: [2022-12-02 10:52:37,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +22: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +18: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +35: [2022-12-02 10:52:37,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt... +61: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +32: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +61: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:37,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:37,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:37,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +61: [2022-12-02 10:52:37,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +31: [2022-12-02 10:52:37,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +18: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +32: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +18: [2022-12-02 10:52:37,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +32: [2022-12-02 10:52:37,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +32: [2022-12-02 10:52:37,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +32: [2022-12-02 10:52:37,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +16: [2022-12-02 10:52:37,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +35: [2022-12-02 10:52:37,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:37,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +31: [2022-12-02 10:52:37,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +35: [2022-12-02 10:52:37,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +19: [2022-12-02 10:52:37,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +24: [2022-12-02 10:52:37,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +35: [2022-12-02 10:52:37,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +19: [2022-12-02 10:52:37,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +63: [2022-12-02 10:52:37,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +24: [2022-12-02 10:52:37,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +19: [2022-12-02 10:52:37,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +63: [2022-12-02 10:52:37,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +18: [2022-12-02 10:52:37,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +28: [2022-12-02 10:52:37,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +19: [2022-12-02 10:52:37,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +16: [2022-12-02 10:52:37,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +34: [2022-12-02 10:52:37,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:37,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +61: [2022-12-02 10:52:37,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 5: [2022-12-02 10:52:37,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:37,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +39: [2022-12-02 10:52:37,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +26: [2022-12-02 10:52:37,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +55: [2022-12-02 10:52:37,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +55: [2022-12-02 10:52:37,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +22: [2022-12-02 10:52:37,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +40: [2022-12-02 10:52:37,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +19: [2022-12-02 10:52:37,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +13: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +39: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +13: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +40: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +40: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +28: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +40: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +22: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +26: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +28: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:37,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +40: [2022-12-02 10:52:37,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. + 2: [2022-12-02 10:52:37,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_13-model_00-model_states.pt. +40: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +35: [2022-12-02 10:52:37,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +26: [2022-12-02 10:52:37,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +26: [2022-12-02 10:52:37,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +61: [2022-12-02 10:52:37,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +13: [2022-12-02 10:52:37,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +55: [2022-12-02 10:52:37,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:37,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:37,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +22: [2022-12-02 10:52:37,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +55: [2022-12-02 10:52:37,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:37,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:37,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:37,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:37,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +55: [2022-12-02 10:52:37,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +26: [2022-12-02 10:52:37,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:37,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +26: [2022-12-02 10:52:37,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:37,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,476] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +22: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +26: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:37,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:37,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,480] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +13: [2022-12-02 10:52:37,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +35: [2022-12-02 10:52:37,481] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:37,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +13: [2022-12-02 10:52:37,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:37,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:37,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +35: [2022-12-02 10:52:37,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,488] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +41: [2022-12-02 10:52:37,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +63: [2022-12-02 10:52:37,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:37,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:37,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:37,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +35: [2022-12-02 10:52:37,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:37,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:37,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +61: [2022-12-02 10:52:37,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:37,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +63: [2022-12-02 10:52:37,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:37,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,524] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +43: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +53: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +39: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +34: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +34: [2022-12-02 10:52:37,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:37,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:37,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +42: [2022-12-02 10:52:37,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:37,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +47: [2022-12-02 10:52:37,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +40: [2022-12-02 10:52:37,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,568] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +41: [2022-12-02 10:52:37,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +40: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:37,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:37,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:37,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:37,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:37,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +39: [2022-12-02 10:52:37,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:37,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,607] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +41: [2022-12-02 10:52:37,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:37,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +58: [2022-12-02 10:52:37,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:37,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +48: [2022-12-02 10:52:37,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:37,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:37,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +44: [2022-12-02 10:52:37,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +60: [2022-12-02 10:52:37,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +58: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,635] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +49: [2022-12-02 10:52:37,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:37,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +33: [2022-12-02 10:52:37,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:37,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:37,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:37,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +46: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +45: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +52: [2022-12-02 10:52:37,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +59: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +36: [2022-12-02 10:52:37,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +47: [2022-12-02 10:52:37,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:37,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +43: [2022-12-02 10:52:37,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +53: [2022-12-02 10:52:37,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:37,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:37,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:37,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +57: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +42: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +37: [2022-12-02 10:52:37,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +57: [2022-12-02 10:52:37,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:37,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:37,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:37,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +54: [2022-12-02 10:52:37,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:37,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +56: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +36: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +51: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt... +59: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:37,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:37,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:37,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +44: [2022-12-02 10:52:37,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:37,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:37,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:37,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +50: [2022-12-02 10:52:37,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:37,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:37,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:37,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +46: [2022-12-02 10:52:37,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:37,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +48: [2022-12-02 10:52:37,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:37,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +62: [2022-12-02 10:52:37,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:37,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:37,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +60: [2022-12-02 10:52:37,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:37,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:37,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:37,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:37,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:37,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:37,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:37,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:37,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +50: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:37,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:37,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:37,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:37,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:37,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:37,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:37,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:37,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:37,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:37,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:37,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:37,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:37,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:37,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +49: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +33: [2022-12-02 10:52:37,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:37,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:37,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:37,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:37,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:37,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:37,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +37: [2022-12-02 10:52:37,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +52: [2022-12-02 10:52:37,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +52: [2022-12-02 10:52:37,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +51: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +54: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +56: [2022-12-02 10:52:37,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +52: [2022-12-02 10:52:37,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. +51: [2022-12-02 10:52:37,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_34-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:37,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:37,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:37,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:37,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:37,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +45: [2022-12-02 10:52:37,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:37,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:37,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +37: [2022-12-02 10:52:37,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +37: [2022-12-02 10:52:37,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:37,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:37,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:37,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:37,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:37,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +56: [2022-12-02 10:52:37,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:37,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:37,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:37,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +54: [2022-12-02 10:52:37,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +38: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +38: [2022-12-02 10:52:37,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:37,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:37,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:37,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:37,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +38: [2022-12-02 10:52:37,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:37,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +27: [2022-12-02 10:52:37,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +62: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +20: [2022-12-02 10:52:37,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +62: [2022-12-02 10:52:37,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:37,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +62: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +20: [2022-12-02 10:52:37,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +12: [2022-12-02 10:52:37,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +32: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +32: [2022-12-02 10:52:37,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +12: [2022-12-02 10:52:37,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +32: [2022-12-02 10:52:37,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +32: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +15: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +32: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +14: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:37,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:37,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +61: [2022-12-02 10:52:37,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:37,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. + 1: [2022-12-02 10:52:37,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:37,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +61: [2022-12-02 10:52:37,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +25: [2022-12-02 10:52:37,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:37,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:37,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +23: [2022-12-02 10:52:37,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:37,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:37,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:37,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +27: [2022-12-02 10:52:37,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:37,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +61: [2022-12-02 10:52:37,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +25: [2022-12-02 10:52:37,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +32: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +21: [2022-12-02 10:52:37,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 3: [2022-12-02 10:52:37,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:37,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +24: [2022-12-02 10:52:37,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-02 10:52:37,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +19: [2022-12-02 10:52:37,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +20: [2022-12-02 10:52:37,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-02 10:52:37,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +21: [2022-12-02 10:52:37,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +15: [2022-12-02 10:52:37,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +27: [2022-12-02 10:52:37,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:37,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:37,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:37,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +30: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +25: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +23: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:37,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:37,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +20: [2022-12-02 10:52:37,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +25: [2022-12-02 10:52:37,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:37,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +15: [2022-12-02 10:52:37,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +12: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +12: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +23: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 8: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +14: [2022-12-02 10:52:37,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:37,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +20: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +23: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +27: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:37,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +23: [2022-12-02 10:52:37,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-02 10:52:37,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:37,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:37,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +30: [2022-12-02 10:52:37,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:37,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:37,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:37,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:37,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:37,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +25: [2022-12-02 10:52:37,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:37,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:37,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +30: [2022-12-02 10:52:37,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:37,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:37,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +28: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +17: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +11: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +63: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 8: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +17: [2022-12-02 10:52:37,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:37,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:37,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +17: [2022-12-02 10:52:37,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:37,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 6: [2022-12-02 10:52:37,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:37,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-02 10:52:37,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:37,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:37,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +17: [2022-12-02 10:52:37,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:37,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:37,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:37,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:37,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:37,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:37,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:37,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:37,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:37,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:37,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:37,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:37,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +13: [2022-12-02 10:52:37,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:37,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:37,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +28: [2022-12-02 10:52:37,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +14: [2022-12-02 10:52:37,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:37,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:37,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:37,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:37,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:37,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:37,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +18: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +32: [2022-12-02 10:52:38,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +14: [2022-12-02 10:52:38,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,010] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:38,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:38,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:38,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +22: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +34: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +22: [2022-12-02 10:52:38,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +11: [2022-12-02 10:52:38,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +32: [2022-12-02 10:52:38,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +24: [2022-12-02 10:52:38,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:38,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +31: [2022-12-02 10:52:38,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:38,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +14: [2022-12-02 10:52:38,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +31: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +61: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +14: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +21: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +40: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +24: [2022-12-02 10:52:38,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:38,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:38,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:38,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +31: [2022-12-02 10:52:38,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +31: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +40: [2022-12-02 10:52:38,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +19: [2022-12-02 10:52:38,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +40: [2022-12-02 10:52:38,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +28: [2022-12-02 10:52:38,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +40: [2022-12-02 10:52:38,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +40: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +40: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +28: [2022-12-02 10:52:38,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:38,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:38,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +19: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +29: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +35: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +28: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +35: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +28: [2022-12-02 10:52:38,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +35: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:38,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +16: [2022-12-02 10:52:38,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:38,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:38,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:38,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:38,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +16: [2022-12-02 10:52:38,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,064] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +21: [2022-12-02 10:52:38,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:38,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +24: [2022-12-02 10:52:38,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +61: [2022-12-02 10:52:38,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:38,073] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,073] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +61: [2022-12-02 10:52:38,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:38,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +61: [2022-12-02 10:52:38,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +26: [2022-12-02 10:52:38,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:38,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +39: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +10: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +61: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +19: [2022-12-02 10:52:38,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +61: [2022-12-02 10:52:38,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +13: [2022-12-02 10:52:38,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +13: [2022-12-02 10:52:38,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:38,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +26: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +63: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +21: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +39: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +26: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +26: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:38,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +21: [2022-12-02 10:52:38,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +33: [2022-12-02 10:52:38,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +13: [2022-12-02 10:52:38,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:38,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:38,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:38,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +10: [2022-12-02 10:52:38,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt... +39: [2022-12-02 10:52:38,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +63: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +18: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +33: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +19: [2022-12-02 10:52:38,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +19: [2022-12-02 10:52:38,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:38,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:38,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +22: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +22: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +22: [2022-12-02 10:52:38,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:38,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +18: [2022-12-02 10:52:38,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:38,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +31: [2022-12-02 10:52:38,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +18: [2022-12-02 10:52:38,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +34: [2022-12-02 10:52:38,108] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +34: [2022-12-02 10:52:38,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +31: [2022-12-02 10:52:38,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,113] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,114] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,115] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +40: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +13: [2022-12-02 10:52:38,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +58: [2022-12-02 10:52:38,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +29: [2022-12-02 10:52:38,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +18: [2022-12-02 10:52:38,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +29: [2022-12-02 10:52:38,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +58: [2022-12-02 10:52:38,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +18: [2022-12-02 10:52:38,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +59: [2022-12-02 10:52:38,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +18: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +29: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +58: [2022-12-02 10:52:38,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +13: [2022-12-02 10:52:38,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +13: [2022-12-02 10:52:38,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +35: [2022-12-02 10:52:38,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:38,129] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +18: [2022-12-02 10:52:38,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,136] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +31: [2022-12-02 10:52:38,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +55: [2022-12-02 10:52:38,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +48: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +31: [2022-12-02 10:52:38,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +48: [2022-12-02 10:52:38,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +22: [2022-12-02 10:52:38,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +48: [2022-12-02 10:52:38,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +22: [2022-12-02 10:52:38,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +34: [2022-12-02 10:52:38,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +31: [2022-12-02 10:52:38,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +10: [2022-12-02 10:52:38,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +31: [2022-12-02 10:52:38,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +29: [2022-12-02 10:52:38,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +50: [2022-12-02 10:52:38,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +31: [2022-12-02 10:52:38,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +45: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +35: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +62: [2022-12-02 10:52:38,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +40: [2022-12-02 10:52:38,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +50: [2022-12-02 10:52:38,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +26: [2022-12-02 10:52:38,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +62: [2022-12-02 10:52:38,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:38,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +10: [2022-12-02 10:52:38,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_14-model_00-model_states.pt. +35: [2022-12-02 10:52:38,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +45: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +29: [2022-12-02 10:52:38,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +26: [2022-12-02 10:52:38,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +10: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +39: [2022-12-02 10:52:38,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +10: [2022-12-02 10:52:38,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +46: [2022-12-02 10:52:38,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:38,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:38,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:38,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:38,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:38,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:38,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +46: [2022-12-02 10:52:38,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +10: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +47: [2022-12-02 10:52:38,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:38,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:38,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:38,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:38,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +10: [2022-12-02 10:52:38,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +36: [2022-12-02 10:52:38,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:38,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:38,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:38,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +26: [2022-12-02 10:52:38,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +60: [2022-12-02 10:52:38,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +47: [2022-12-02 10:52:38,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +26: [2022-12-02 10:52:38,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +60: [2022-12-02 10:52:38,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +43: [2022-12-02 10:52:38,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +10: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +48: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:38,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:38,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:38,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:38,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +47: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +60: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +55: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +55: [2022-12-02 10:52:38,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:38,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:38,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:38,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +33: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +33: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:38,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:38,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +41: [2022-12-02 10:52:38,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:38,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +41: [2022-12-02 10:52:38,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:38,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +57: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:38,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:38,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +42: [2022-12-02 10:52:38,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +39: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:38,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +51: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +44: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +58: [2022-12-02 10:52:38,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:38,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +53: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +49: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +58: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +59: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:38,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +59: [2022-12-02 10:52:38,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +59: [2022-12-02 10:52:38,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:38,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +38: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:38,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +45: [2022-12-02 10:52:38,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:38,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +36: [2022-12-02 10:52:38,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +48: [2022-12-02 10:52:38,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:38,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +48: [2022-12-02 10:52:38,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:38,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:38,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:38,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +56: [2022-12-02 10:52:38,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +62: [2022-12-02 10:52:38,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:38,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:38,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +50: [2022-12-02 10:52:38,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +32: [2022-12-02 10:52:38,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:38,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +57: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +47: [2022-12-02 10:52:38,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +52: [2022-12-02 10:52:38,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +62: [2022-12-02 10:52:38,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:38,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:38,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +45: [2022-12-02 10:52:38,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +53: [2022-12-02 10:52:38,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +38: [2022-12-02 10:52:38,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +60: [2022-12-02 10:52:38,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +49: [2022-12-02 10:52:38,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,331] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +43: [2022-12-02 10:52:38,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +44: [2022-12-02 10:52:38,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +51: [2022-12-02 10:52:38,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +46: [2022-12-02 10:52:38,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:38,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:38,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:38,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +37: [2022-12-02 10:52:38,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +37: [2022-12-02 10:52:38,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:38,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +43: [2022-12-02 10:52:38,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +54: [2022-12-02 10:52:38,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt... +52: [2022-12-02 10:52:38,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +42: [2022-12-02 10:52:38,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +56: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +36: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,365] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +61: [2022-12-02 10:52:38,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,388] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:38,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +35: [2022-12-02 10:52:38,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +54: [2022-12-02 10:52:38,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_35-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +32: [2022-12-02 10:52:38,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +34: [2022-12-02 10:52:38,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +34: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +35: [2022-12-02 10:52:38,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +35: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +35: [2022-12-02 10:52:38,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +30: [2022-12-02 10:52:38,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +35: [2022-12-02 10:52:38,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +30: [2022-12-02 10:52:38,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +35: [2022-12-02 10:52:38,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +30: [2022-12-02 10:52:38,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +35: [2022-12-02 10:52:38,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:38,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +34: [2022-12-02 10:52:38,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +63: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +25: [2022-12-02 10:52:38,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +25: [2022-12-02 10:52:38,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +34: [2022-12-02 10:52:38,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +61: [2022-12-02 10:52:38,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:38,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +61: [2022-12-02 10:52:38,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +61: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +35: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +20: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +23: [2022-12-02 10:52:38,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +23: [2022-12-02 10:52:38,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +20: [2022-12-02 10:52:38,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,547] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:38,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:38,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:38,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:38,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +63: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +35: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,551] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +39: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +20: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +20: [2022-12-02 10:52:38,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +55: [2022-12-02 10:52:38,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +63: [2022-12-02 10:52:38,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +55: [2022-12-02 10:52:38,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +17: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +17: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +17: [2022-12-02 10:52:38,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:38,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:38,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:38,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +17: [2022-12-02 10:52:38,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,594] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +30: [2022-12-02 10:52:38,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +41: [2022-12-02 10:52:38,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +25: [2022-12-02 10:52:38,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +25: [2022-12-02 10:52:38,600] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:38,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +39: [2022-12-02 10:52:38,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,606] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:38,605] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +30: [2022-12-02 10:52:38,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +15: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:38,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +39: [2022-12-02 10:52:38,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +23: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 1: [2022-12-02 10:52:38,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:38,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +30: [2022-12-02 10:52:38,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:38,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:38,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:38,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +27: [2022-12-02 10:52:38,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +55: [2022-12-02 10:52:38,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +55: [2022-12-02 10:52:38,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +55: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +55: [2022-12-02 10:52:38,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +20: [2022-12-02 10:52:38,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:38,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +25: [2022-12-02 10:52:38,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +25: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 8: [2022-12-02 10:52:38,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:38,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +28: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +14: [2022-12-02 10:52:38,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +39: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +39: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +14: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,650] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:38,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:38,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +48: [2022-12-02 10:52:38,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +19: [2022-12-02 10:52:38,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +30: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +20: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +59: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +30: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +59: [2022-12-02 10:52:38,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +19: [2022-12-02 10:52:38,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +23: [2022-12-02 10:52:38,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +30: [2022-12-02 10:52:38,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +48: [2022-12-02 10:52:38,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:38,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:38,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:38,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:38,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:38,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +23: [2022-12-02 10:52:38,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:38,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:38,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +19: [2022-12-02 10:52:38,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +19: [2022-12-02 10:52:38,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +17: [2022-12-02 10:52:38,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +19: [2022-12-02 10:52:38,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +41: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,675] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +20: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +58: [2022-12-02 10:52:38,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:38,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +20: [2022-12-02 10:52:38,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:38,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:38,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:38,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:38,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:38,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +40: [2022-12-02 10:52:38,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +39: [2022-12-02 10:52:38,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +39: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +39: [2022-12-02 10:52:38,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +27: [2022-12-02 10:52:38,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +39: [2022-12-02 10:52:38,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +12: [2022-12-02 10:52:38,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +12: [2022-12-02 10:52:38,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:38,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:38,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +36: [2022-12-02 10:52:38,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +15: [2022-12-02 10:52:38,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +42: [2022-12-02 10:52:38,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +45: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +33: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:38,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +33: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +45: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +45: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +56: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +17: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:38,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +36: [2022-12-02 10:52:38,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +17: [2022-12-02 10:52:38,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:38,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:38,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +45: [2022-12-02 10:52:38,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +17: [2022-12-02 10:52:38,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +28: [2022-12-02 10:52:38,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +42: [2022-12-02 10:52:38,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +14: [2022-12-02 10:52:38,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +56: [2022-12-02 10:52:38,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:38,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +41: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +42: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +27: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +50: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +27: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +52: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +45: [2022-12-02 10:52:38,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:38,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +56: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +27: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +41: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +43: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +41: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +27: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +47: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +47: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +47: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +27: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:38,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +41: [2022-12-02 10:52:38,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:38,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +50: [2022-12-02 10:52:38,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +36: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:38,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +47: [2022-12-02 10:52:38,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +48: [2022-12-02 10:52:38,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +46: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +62: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +14: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +62: [2022-12-02 10:52:38,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +21: [2022-12-02 10:52:38,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +59: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +21: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +59: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +49: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +13: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +62: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +22: [2022-12-02 10:52:38,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +62: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +22: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +48: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +18: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +15: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +47: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +47: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +15: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +47: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +47: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +59: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +59: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +19: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +59: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +49: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +38: [2022-12-02 10:52:38,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +19: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +49: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +28: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +38: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +28: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +58: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +15: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:38,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +18: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +28: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 7: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 7: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +62: [2022-12-02 10:52:38,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +22: [2022-12-02 10:52:38,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +62: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +21: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +21: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +62: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +13: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +13: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +60: [2022-12-02 10:52:38,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +22: [2022-12-02 10:52:38,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +22: [2022-12-02 10:52:38,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +60: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +18: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +14: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +18: [2022-12-02 10:52:38,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +28: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +58: [2022-12-02 10:52:38,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +11: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +60: [2022-12-02 10:52:38,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +58: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +19: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +27: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +60: [2022-12-02 10:52:38,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +60: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +27: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +27: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +40: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 6: [2022-12-02 10:52:38,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +51: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +57: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +11: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... + 6: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +14: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +12: [2022-12-02 10:52:38,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +14: [2022-12-02 10:52:38,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:38,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:38,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:38,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:38,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:38,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:38,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +44: [2022-12-02 10:52:38,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +12: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +44: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +19: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +16: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +16: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +51: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +51: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:38,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +16: [2022-12-02 10:52:38,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +45: [2022-12-02 10:52:38,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +45: [2022-12-02 10:52:38,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:38,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:38,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +57: [2022-12-02 10:52:38,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +59: [2022-12-02 10:52:38,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:38,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:38,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:38,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +57: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +51: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +59: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +44: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +48: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +56: [2022-12-02 10:52:38,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +37: [2022-12-02 10:52:38,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +24: [2022-12-02 10:52:38,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +56: [2022-12-02 10:52:38,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:38,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +28: [2022-12-02 10:52:38,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +40: [2022-12-02 10:52:38,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 9: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +44: [2022-12-02 10:52:38,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +28: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +58: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +48: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +44: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +28: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +43: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +29: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +44: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +44: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +29: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +58: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +28: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:38,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +58: [2022-12-02 10:52:38,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +28: [2022-12-02 10:52:38,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:38,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:38,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:38,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +33: [2022-12-02 10:52:38,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +58: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +42: [2022-12-02 10:52:38,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +19: [2022-12-02 10:52:38,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:38,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +24: [2022-12-02 10:52:38,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +40: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +19: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +43: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +43: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +33: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 0: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +43: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +24: [2022-12-02 10:52:38,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +53: [2022-12-02 10:52:38,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +52: [2022-12-02 10:52:38,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +24: [2022-12-02 10:52:38,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +54: [2022-12-02 10:52:38,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +33: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +24: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +24: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +54: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +19: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:38,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +50: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +53: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +45: [2022-12-02 10:52:38,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:38,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:38,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:38,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +54: [2022-12-02 10:52:38,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +54: [2022-12-02 10:52:38,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt... +18: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +56: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +56: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +40: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:38,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +46: [2022-12-02 10:52:38,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +12: [2022-12-02 10:52:38,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +49: [2022-12-02 10:52:38,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +12: [2022-12-02 10:52:38,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-02 10:52:38,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +32: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +12: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +45: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +12: [2022-12-02 10:52:38,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +45: [2022-12-02 10:52:38,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +45: [2022-12-02 10:52:38,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:38,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +38: [2022-12-02 10:52:38,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +12: [2022-12-02 10:52:38,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:38,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +12: [2022-12-02 10:52:38,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:38,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:38,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 3: [2022-12-02 10:52:38,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +40: [2022-12-02 10:52:38,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 3: [2022-12-02 10:52:38,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-02 10:52:38,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:38,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:38,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +45: [2022-12-02 10:52:38,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +45: [2022-12-02 10:52:38,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:38,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +32: [2022-12-02 10:52:38,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:38,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +21: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +46: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +13: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +36: [2022-12-02 10:52:38,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +49: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +43: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +13: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +32: [2022-12-02 10:52:38,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +32: [2022-12-02 10:52:38,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +26: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +56: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:38,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +47: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +31: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +60: [2022-12-02 10:52:38,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +22: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +22: [2022-12-02 10:52:38,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +43: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +21: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +47: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +33: [2022-12-02 10:52:38,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:38,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +46: [2022-12-02 10:52:38,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +13: [2022-12-02 10:52:38,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +13: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +42: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +18: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +62: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +31: [2022-12-02 10:52:38,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +60: [2022-12-02 10:52:38,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +18: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +42: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +18: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +56: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +31: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +46: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +31: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +31: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +62: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:38,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:38,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +11: [2022-12-02 10:52:38,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +34: [2022-12-02 10:52:38,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +18: [2022-12-02 10:52:38,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +34: [2022-12-02 10:52:38,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +11: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +42: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:38,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +33: [2022-12-02 10:52:38,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:38,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:38,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +52: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +50: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:38,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +50: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +33: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:38,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:38,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:38,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:38,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 5: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +52: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +52: [2022-12-02 10:52:38,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +60: [2022-12-02 10:52:38,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +26: [2022-12-02 10:52:38,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +49: [2022-12-02 10:52:38,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +46: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +26: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +26: [2022-12-02 10:52:38,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +57: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +51: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +13: [2022-12-02 10:52:38,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +11: [2022-12-02 10:52:38,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:38,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:38,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 4: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +57: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +11: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +57: [2022-12-02 10:52:38,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 4: [2022-12-02 10:52:38,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:38,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:38,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:38,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:38,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +26: [2022-12-02 10:52:38,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:38,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +21: [2022-12-02 10:52:38,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:38,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +16: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +38: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +38: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +38: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +38: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:38,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +37: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +10: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +13: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +18: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:38,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:38,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +10: [2022-12-02 10:52:38,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +46: [2022-12-02 10:52:38,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +38: [2022-12-02 10:52:38,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +22: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +45: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +22: [2022-12-02 10:52:38,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +45: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +10: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +10: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt... +26: [2022-12-02 10:52:38,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +35: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +51: [2022-12-02 10:52:38,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:38,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:38,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:38,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:38,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:38,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +49: [2022-12-02 10:52:38,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +22: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +22: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:38,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +63: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +37: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +37: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +29: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +37: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +47: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +22: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:38,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +21: [2022-12-02 10:52:38,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +18: [2022-12-02 10:52:38,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:38,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +11: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +35: [2022-12-02 10:52:38,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +18: [2022-12-02 10:52:38,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +62: [2022-12-02 10:52:38,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +35: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +35: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +18: [2022-12-02 10:52:38,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:38,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +18: [2022-12-02 10:52:38,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:38,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:38,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +24: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +36: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +24: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +53: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +53: [2022-12-02 10:52:38,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +62: [2022-12-02 10:52:38,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:38,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +11: [2022-12-02 10:52:38,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +62: [2022-12-02 10:52:38,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +13: [2022-12-02 10:52:38,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:38,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +13: [2022-12-02 10:52:38,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:38,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +63: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:38,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +44: [2022-12-02 10:52:38,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +36: [2022-12-02 10:52:38,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:38,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +44: [2022-12-02 10:52:38,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:38,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +16: [2022-12-02 10:52:38,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:38,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +54: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_36-model_00-model_states.pt. +26: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-02 10:52:38,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:38,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:38,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +11: [2022-12-02 10:52:38,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-02 10:52:38,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 2: [2022-12-02 10:52:38,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:38,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +11: [2022-12-02 10:52:38,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:38,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:38,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +60: [2022-12-02 10:52:38,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +26: [2022-12-02 10:52:38,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:38,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +57: [2022-12-02 10:52:38,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:38,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:38,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:38,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +16: [2022-12-02 10:52:38,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +16: [2022-12-02 10:52:38,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +16: [2022-12-02 10:52:38,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +57: [2022-12-02 10:52:38,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:38,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:38,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +16: [2022-12-02 10:52:38,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +57: [2022-12-02 10:52:38,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:38,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:38,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:38,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +24: [2022-12-02 10:52:38,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:38,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +31: [2022-12-02 10:52:38,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +32: [2022-12-02 10:52:38,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +29: [2022-12-02 10:52:38,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +34: [2022-12-02 10:52:38,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +29: [2022-12-02 10:52:38,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +29: [2022-12-02 10:52:38,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:38,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +29: [2022-12-02 10:52:38,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:38,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:38,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:38,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +31: [2022-12-02 10:52:38,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +29: [2022-12-02 10:52:38,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +24: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:38,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +29: [2022-12-02 10:52:38,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:38,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +32: [2022-12-02 10:52:38,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:38,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:38,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:38,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:38,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:38,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +32: [2022-12-02 10:52:38,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +54: [2022-12-02 10:52:38,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:38,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:38,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:38,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:38,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:38,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:38,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +10: [2022-12-02 10:52:38,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +44: [2022-12-02 10:52:38,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +10: [2022-12-02 10:52:38,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +61: [2022-12-02 10:52:38,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +31: [2022-12-02 10:52:38,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:38,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +34: [2022-12-02 10:52:38,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +10: [2022-12-02 10:52:38,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +31: [2022-12-02 10:52:38,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +34: [2022-12-02 10:52:38,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:38,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +10: [2022-12-02 10:52:38,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +10: [2022-12-02 10:52:38,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_15-model_00-model_states.pt. +34: [2022-12-02 10:52:38,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:38,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:38,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +31: [2022-12-02 10:52:38,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +35: [2022-12-02 10:52:38,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:38,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:38,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:38,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +31: [2022-12-02 10:52:38,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:38,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:38,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +63: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:38,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:38,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:38,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:38,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:38,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:38,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:38,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:38,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:38,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +10: [2022-12-02 10:52:38,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:38,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:38,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +39: [2022-12-02 10:52:38,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +10: [2022-12-02 10:52:38,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +10: [2022-12-02 10:52:38,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +61: [2022-12-02 10:52:38,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:38,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +10: [2022-12-02 10:52:38,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:38,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:38,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:38,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:38,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:38,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:38,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,009] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +39: [2022-12-02 10:52:39,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +55: [2022-12-02 10:52:39,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +39: [2022-12-02 10:52:39,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:39,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +55: [2022-12-02 10:52:39,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +39: [2022-12-02 10:52:39,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +39: [2022-12-02 10:52:39,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +39: [2022-12-02 10:52:39,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +39: [2022-12-02 10:52:39,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,129] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,139] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +17: [2022-12-02 10:52:39,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +46: [2022-12-02 10:52:39,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +23: [2022-12-02 10:52:39,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:39,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:39,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:39,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +30: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +40: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +23: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:39,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +23: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:39,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:39,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:39,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:39,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +46: [2022-12-02 10:52:39,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +41: [2022-12-02 10:52:39,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:39,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,174] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +41: [2022-12-02 10:52:39,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,175] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +41: [2022-12-02 10:52:39,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +41: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +40: [2022-12-02 10:52:39,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +30: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +25: [2022-12-02 10:52:39,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +25: [2022-12-02 10:52:39,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +42: [2022-12-02 10:52:39,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,194] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +36: [2022-12-02 10:52:39,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:39,197] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +52: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:39,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +52: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:39,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:39,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +42: [2022-12-02 10:52:39,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:39,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:39,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +43: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +17: [2022-12-02 10:52:39,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +41: [2022-12-02 10:52:39,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +41: [2022-12-02 10:52:39,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:39,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:39,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +36: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +36: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +41: [2022-12-02 10:52:39,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +43: [2022-12-02 10:52:39,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +43: [2022-12-02 10:52:39,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +41: [2022-12-02 10:52:39,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,226] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +41: [2022-12-02 10:52:39,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +57: [2022-12-02 10:52:39,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +17: [2022-12-02 10:52:39,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +47: [2022-12-02 10:52:39,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +57: [2022-12-02 10:52:39,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:39,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +57: [2022-12-02 10:52:39,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:39,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:39,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +17: [2022-12-02 10:52:39,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +47: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +57: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +57: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +23: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:39,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:39,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:39,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:39,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +27: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +40: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +27: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:39,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +17: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +46: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +17: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +56: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:39,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:39,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,263] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +56: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +15: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:39,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:39,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:39,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +20: [2022-12-02 10:52:39,266] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +44: [2022-12-02 10:52:39,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +17: [2022-12-02 10:52:39,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +51: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +51: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:39,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +17: [2022-12-02 10:52:39,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,269] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +36: [2022-12-02 10:52:39,270] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +15: [2022-12-02 10:52:39,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:39,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,271] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +23: [2022-12-02 10:52:39,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:39,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:39,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:39,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +23: [2022-12-02 10:52:39,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +44: [2022-12-02 10:52:39,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +30: [2022-12-02 10:52:39,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +30: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +30: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +44: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +59: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:39,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +23: [2022-12-02 10:52:39,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +42: [2022-12-02 10:52:39,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +52: [2022-12-02 10:52:39,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:39,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +56: [2022-12-02 10:52:39,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +20: [2022-12-02 10:52:39,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +56: [2022-12-02 10:52:39,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:39,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +52: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:39,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:39,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:39,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:39,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +43: [2022-12-02 10:52:39,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +43: [2022-12-02 10:52:39,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +56: [2022-12-02 10:52:39,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +47: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +36: [2022-12-02 10:52:39,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +56: [2022-12-02 10:52:39,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +40: [2022-12-02 10:52:39,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +46: [2022-12-02 10:52:39,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +20: [2022-12-02 10:52:39,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +20: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,312] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,313] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +57: [2022-12-02 10:52:39,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +27: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +36: [2022-12-02 10:52:39,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +30: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +53: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +52: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +30: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +57: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:39,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +53: [2022-12-02 10:52:39,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +61: [2022-12-02 10:52:39,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +20: [2022-12-02 10:52:39,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +30: [2022-12-02 10:52:39,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +30: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +61: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +61: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,323] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +42: [2022-12-02 10:52:39,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:39,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:39,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +42: [2022-12-02 10:52:39,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +48: [2022-12-02 10:52:39,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +43: [2022-12-02 10:52:39,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +49: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +61: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +48: [2022-12-02 10:52:39,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,332] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +20: [2022-12-02 10:52:39,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +43: [2022-12-02 10:52:39,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +20: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +42: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +38: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +19: [2022-12-02 10:52:39,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +47: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +47: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +42: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +38: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +61: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +27: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +14: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,339] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,340] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +27: [2022-12-02 10:52:39,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +52: [2022-12-02 10:52:39,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +12: [2022-12-02 10:52:39,341] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +12: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +52: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +12: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:39,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:39,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +12: [2022-12-02 10:52:39,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +51: [2022-12-02 10:52:39,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +15: [2022-12-02 10:52:39,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +52: [2022-12-02 10:52:39,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,343] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:39,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:39,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:39,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:39,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +43: [2022-12-02 10:52:39,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +14: [2022-12-02 10:52:39,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:39,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:39,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +63: [2022-12-02 10:52:39,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,346] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +38: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:39,347] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +21: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +21: [2022-12-02 10:52:39,348] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +38: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +21: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +21: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:39,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:39,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:39,351] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +14: [2022-12-02 10:52:39,352] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:39,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +37: [2022-12-02 10:52:39,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +62: [2022-12-02 10:52:39,353] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,354] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,355] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +15: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +57: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +51: [2022-12-02 10:52:39,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +57: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +57: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +63: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +63: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +63: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +54: [2022-12-02 10:52:39,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +57: [2022-12-02 10:52:39,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +34: [2022-12-02 10:52:39,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +16: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +34: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +60: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +16: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +34: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +16: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +36: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:39,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +16: [2022-12-02 10:52:39,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +44: [2022-12-02 10:52:39,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +16: [2022-12-02 10:52:39,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:39,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +45: [2022-12-02 10:52:39,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:39,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +44: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +50: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +45: [2022-12-02 10:52:39,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,373] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +15: [2022-12-02 10:52:39,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +35: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +35: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:39,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +28: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +54: [2022-12-02 10:52:39,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +28: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +34: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +54: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +37: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +54: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +54: [2022-12-02 10:52:39,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt... +47: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +47: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +27: [2022-12-02 10:52:39,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +60: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +27: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +60: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +28: [2022-12-02 10:52:39,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +27: [2022-12-02 10:52:39,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +15: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +58: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +58: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +48: [2022-12-02 10:52:39,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +15: [2022-12-02 10:52:39,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +37: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +28: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +59: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +28: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:39,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +28: [2022-12-02 10:52:39,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:39,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:39,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +15: [2022-12-02 10:52:39,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +51: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +15: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +15: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +18: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +33: [2022-12-02 10:52:39,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +15: [2022-12-02 10:52:39,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:39,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +51: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +15: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +53: [2022-12-02 10:52:39,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +18: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +49: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +53: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +49: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +59: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +24: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +59: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +29: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +59: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +29: [2022-12-02 10:52:39,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +59: [2022-12-02 10:52:39,403] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,405] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +33: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:39,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +18: [2022-12-02 10:52:39,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:39,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +32: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +12: [2022-12-02 10:52:39,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +60: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:39,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:39,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:39,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +18: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +44: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:39,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +49: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +44: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +29: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +24: [2022-12-02 10:52:39,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:39,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:39,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +29: [2022-12-02 10:52:39,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +12: [2022-12-02 10:52:39,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +44: [2022-12-02 10:52:39,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:39,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:39,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +14: [2022-12-02 10:52:39,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +44: [2022-12-02 10:52:39,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:39,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +32: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +21: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +38: [2022-12-02 10:52:39,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +21: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +13: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +59: [2022-12-02 10:52:39,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +26: [2022-12-02 10:52:39,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +60: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +60: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +38: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +38: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +38: [2022-12-02 10:52:39,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +19: [2022-12-02 10:52:39,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +45: [2022-12-02 10:52:39,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +61: [2022-12-02 10:52:39,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +22: [2022-12-02 10:52:39,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +53: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +48: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +19: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +48: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +13: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +48: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +22: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +45: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +22: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +14: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +14: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +21: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +21: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +53: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +19: [2022-12-02 10:52:39,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +63: [2022-12-02 10:52:39,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,437] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +63: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +26: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +26: [2022-12-02 10:52:39,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:39,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +26: [2022-12-02 10:52:39,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:39,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +26: [2022-12-02 10:52:39,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,442] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +49: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +16: [2022-12-02 10:52:39,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:39,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +22: [2022-12-02 10:52:39,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,445] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +53: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +55: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,446] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,447] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:39,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +16: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +55: [2022-12-02 10:52:39,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +16: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +16: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +50: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +62: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,450] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +12: [2022-12-02 10:52:39,451] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +62: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +14: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +54: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +35: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +34: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +48: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +12: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +12: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,453] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +12: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +62: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +62: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +35: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +14: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +62: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +14: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +50: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +50: [2022-12-02 10:52:39,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +35: [2022-12-02 10:52:39,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,457] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +19: [2022-12-02 10:52:39,458] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +34: [2022-12-02 10:52:39,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +19: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,459] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +12: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +12: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,460] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +21: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +48: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +21: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +54: [2022-12-02 10:52:39,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. +54: [2022-12-02 10:52:39,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_37-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +12: [2022-12-02 10:52:39,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +45: [2022-12-02 10:52:39,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +19: [2022-12-02 10:52:39,465] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +58: [2022-12-02 10:52:39,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +21: [2022-12-02 10:52:39,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +45: [2022-12-02 10:52:39,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +45: [2022-12-02 10:52:39,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +19: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +58: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +58: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +58: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +38: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,469] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +14: [2022-12-02 10:52:39,470] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,471] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,472] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,472] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +19: [2022-12-02 10:52:39,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +38: [2022-12-02 10:52:39,473] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +21: [2022-12-02 10:52:39,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +63: [2022-12-02 10:52:39,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +21: [2022-12-02 10:52:39,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,476] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +63: [2022-12-02 10:52:39,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +14: [2022-12-02 10:52:39,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,477] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,478] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +33: [2022-12-02 10:52:39,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +24: [2022-12-02 10:52:39,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +63: [2022-12-02 10:52:39,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +33: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +18: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +54: [2022-12-02 10:52:39,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +29: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +38: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +28: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +63: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +29: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +38: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +38: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +24: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +16: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +16: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +61: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +10: [2022-12-02 10:52:39,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +34: [2022-12-02 10:52:39,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +24: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +24: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +16: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +62: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +16: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +54: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +62: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +34: [2022-12-02 10:52:39,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +16: [2022-12-02 10:52:39,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,494] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +61: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +61: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +18: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +18: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +18: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +61: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +61: [2022-12-02 10:52:39,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +29: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +35: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +29: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +62: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +18: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +11: [2022-12-02 10:52:39,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +35: [2022-12-02 10:52:39,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +35: [2022-12-02 10:52:39,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +58: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 2: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +28: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +35: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +54: [2022-12-02 10:52:39,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +50: [2022-12-02 10:52:39,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,503] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +10: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +10: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +13: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,504] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +50: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +11: [2022-12-02 10:52:39,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +58: [2022-12-02 10:52:39,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +32: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +13: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +26: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +34: [2022-12-02 10:52:39,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +18: [2022-12-02 10:52:39,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:39,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:39,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:39,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +11: [2022-12-02 10:52:39,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:39,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +45: [2022-12-02 10:52:39,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +59: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +45: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +29: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 6: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +35: [2022-12-02 10:52:39,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +58: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +13: [2022-12-02 10:52:39,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +13: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +29: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +18: [2022-12-02 10:52:39,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +26: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +22: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +22: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +33: [2022-12-02 10:52:39,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +24: [2022-12-02 10:52:39,527] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +55: [2022-12-02 10:52:39,527] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +24: [2022-12-02 10:52:39,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +28: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +28: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +29: [2022-12-02 10:52:39,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +24: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +24: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +24: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +24: [2022-12-02 10:52:39,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:39,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +28: [2022-12-02 10:52:39,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:39,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +33: [2022-12-02 10:52:39,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +48: [2022-12-02 10:52:39,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... + 2: [2022-12-02 10:52:39,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:39,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:39,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:39,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:39,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +31: [2022-12-02 10:52:39,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:39,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +32: [2022-12-02 10:52:39,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +32: [2022-12-02 10:52:39,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +32: [2022-12-02 10:52:39,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +22: [2022-12-02 10:52:39,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +13: [2022-12-02 10:52:39,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +26: [2022-12-02 10:52:39,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:39,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:39,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:39,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:39,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +13: [2022-12-02 10:52:39,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +62: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +26: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:39,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:39,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:39,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +31: [2022-12-02 10:52:39,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt... +22: [2022-12-02 10:52:39,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:39,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:39,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:39,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... +45: [2022-12-02 10:52:39,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... + 5: [2022-12-02 10:52:39,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +38: [2022-12-02 10:52:39,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +63: [2022-12-02 10:52:39,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +10: [2022-12-02 10:52:39,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +11: [2022-12-02 10:52:39,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +10: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +10: [2022-12-02 10:52:39,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-02 10:52:39,594] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +11: [2022-12-02 10:52:39,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +11: [2022-12-02 10:52:39,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +34: [2022-12-02 10:52:39,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-02 10:52:39,603] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-02 10:52:39,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +10: [2022-12-02 10:52:39,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +10: [2022-12-02 10:52:39,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +10: [2022-12-02 10:52:39,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +10: [2022-12-02 10:52:39,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +10: [2022-12-02 10:52:39,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +55: [2022-12-02 10:52:39,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +10: [2022-12-02 10:52:39,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +10: [2022-12-02 10:52:39,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +10: [2022-12-02 10:52:39,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +42: [2022-12-02 10:52:39,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +33: [2022-12-02 10:52:39,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +11: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +11: [2022-12-02 10:52:39,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +31: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +31: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... +32: [2022-12-02 10:52:39,638] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +11: [2022-12-02 10:52:39,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:39,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +42: [2022-12-02 10:52:39,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +31: [2022-12-02 10:52:39,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +31: [2022-12-02 10:52:39,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_16-model_00-model_states.pt. +42: [2022-12-02 10:52:39,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +39: [2022-12-02 10:52:39,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +39: [2022-12-02 10:52:39,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +39: [2022-12-02 10:52:39,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +52: [2022-12-02 10:52:39,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +31: [2022-12-02 10:52:39,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +55: [2022-12-02 10:52:39,674] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +31: [2022-12-02 10:52:39,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +31: [2022-12-02 10:52:39,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:39,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,682] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,685] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +31: [2022-12-02 10:52:39,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +56: [2022-12-02 10:52:39,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +31: [2022-12-02 10:52:39,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +56: [2022-12-02 10:52:39,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +31: [2022-12-02 10:52:39,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:39,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +43: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +36: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +36: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +36: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +36: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +25: [2022-12-02 10:52:39,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +37: [2022-12-02 10:52:39,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +30: [2022-12-02 10:52:39,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +30: [2022-12-02 10:52:39,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +41: [2022-12-02 10:52:39,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +57: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +57: [2022-12-02 10:52:39,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +17: [2022-12-02 10:52:39,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +57: [2022-12-02 10:52:39,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +25: [2022-12-02 10:52:39,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +25: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +57: [2022-12-02 10:52:39,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +30: [2022-12-02 10:52:39,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +25: [2022-12-02 10:52:39,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +41: [2022-12-02 10:52:39,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +41: [2022-12-02 10:52:39,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +37: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +30: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +52: [2022-12-02 10:52:39,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +30: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +30: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +30: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +25: [2022-12-02 10:52:39,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +39: [2022-12-02 10:52:39,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +25: [2022-12-02 10:52:39,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +25: [2022-12-02 10:52:39,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +52: [2022-12-02 10:52:39,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +39: [2022-12-02 10:52:39,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +40: [2022-12-02 10:52:39,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +39: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +40: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +39: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +39: [2022-12-02 10:52:39,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +40: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +23: [2022-12-02 10:52:39,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +23: [2022-12-02 10:52:39,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +40: [2022-12-02 10:52:39,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +23: [2022-12-02 10:52:39,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +23: [2022-12-02 10:52:39,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +42: [2022-12-02 10:52:39,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +42: [2022-12-02 10:52:39,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +42: [2022-12-02 10:52:39,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +42: [2022-12-02 10:52:39,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:39,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +51: [2022-12-02 10:52:39,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +43: [2022-12-02 10:52:39,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +56: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +52: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +56: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +52: [2022-12-02 10:52:39,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +46: [2022-12-02 10:52:39,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +60: [2022-12-02 10:52:39,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:39,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 8: [2022-12-02 10:52:39,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +44: [2022-12-02 10:52:39,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... + 8: [2022-12-02 10:52:39,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:39,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +27: [2022-12-02 10:52:39,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +44: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +44: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +39: [2022-12-02 10:52:39,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +60: [2022-12-02 10:52:39,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +52: [2022-12-02 10:52:39,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +46: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +30: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +47: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +27: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +27: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:39,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +60: [2022-12-02 10:52:39,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +17: [2022-12-02 10:52:39,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +47: [2022-12-02 10:52:39,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +25: [2022-12-02 10:52:39,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +47: [2022-12-02 10:52:39,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +37: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +47: [2022-12-02 10:52:39,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +17: [2022-12-02 10:52:39,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +43: [2022-12-02 10:52:39,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +30: [2022-12-02 10:52:39,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +41: [2022-12-02 10:52:39,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +41: [2022-12-02 10:52:39,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +17: [2022-12-02 10:52:39,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +36: [2022-12-02 10:52:39,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +46: [2022-12-02 10:52:39,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +25: [2022-12-02 10:52:39,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +46: [2022-12-02 10:52:39,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +12: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +56: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +25: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +56: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +12: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +56: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +12: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +53: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +46: [2022-12-02 10:52:39,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +46: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +46: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +53: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +46: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +25: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +56: [2022-12-02 10:52:39,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +25: [2022-12-02 10:52:39,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +43: [2022-12-02 10:52:39,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +56: [2022-12-02 10:52:39,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +43: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +12: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +56: [2022-12-02 10:52:39,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +56: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +56: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +25: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +54: [2022-12-02 10:52:39,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +54: [2022-12-02 10:52:39,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +23: [2022-12-02 10:52:39,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +40: [2022-12-02 10:52:39,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +30: [2022-12-02 10:52:39,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:39,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +54: [2022-12-02 10:52:39,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +30: [2022-12-02 10:52:39,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +49: [2022-12-02 10:52:39,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +23: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +40: [2022-12-02 10:52:39,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +30: [2022-12-02 10:52:39,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +47: [2022-12-02 10:52:39,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +30: [2022-12-02 10:52:39,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +17: [2022-12-02 10:52:39,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +40: [2022-12-02 10:52:39,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +15: [2022-12-02 10:52:39,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +15: [2022-12-02 10:52:39,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +47: [2022-12-02 10:52:39,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +15: [2022-12-02 10:52:39,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +37: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +15: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +47: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +15: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +47: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +47: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +47: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +17: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +57: [2022-12-02 10:52:39,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +25: [2022-12-02 10:52:39,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +47: [2022-12-02 10:52:39,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +49: [2022-12-02 10:52:39,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt... +37: [2022-12-02 10:52:39,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +17: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +47: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +17: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +41: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +47: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +47: [2022-12-02 10:52:39,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +17: [2022-12-02 10:52:39,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:39,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +51: [2022-12-02 10:52:39,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +25: [2022-12-02 10:52:39,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +41: [2022-12-02 10:52:39,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +25: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +37: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +57: [2022-12-02 10:52:39,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +25: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +57: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +25: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +57: [2022-12-02 10:52:39,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +57: [2022-12-02 10:52:39,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +39: [2022-12-02 10:52:39,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +25: [2022-12-02 10:52:39,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +25: [2022-12-02 10:52:39,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +36: [2022-12-02 10:52:39,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +37: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +41: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +60: [2022-12-02 10:52:39,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +40: [2022-12-02 10:52:39,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +51: [2022-12-02 10:52:39,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +36: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +30: [2022-12-02 10:52:39,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +36: [2022-12-02 10:52:39,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +36: [2022-12-02 10:52:39,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +36: [2022-12-02 10:52:39,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +23: [2022-12-02 10:52:39,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:39,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:39,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +36: [2022-12-02 10:52:39,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +30: [2022-12-02 10:52:39,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +30: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +42: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +27: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +30: [2022-12-02 10:52:39,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:39,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:39,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:39,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +53: [2022-12-02 10:52:39,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +23: [2022-12-02 10:52:39,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +40: [2022-12-02 10:52:39,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +30: [2022-12-02 10:52:39,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:39,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +23: [2022-12-02 10:52:39,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +40: [2022-12-02 10:52:39,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 1: [2022-12-02 10:52:39,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:39,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +52: [2022-12-02 10:52:39,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +52: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... + 7: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +60: [2022-12-02 10:52:39,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +27: [2022-12-02 10:52:39,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +46: [2022-12-02 10:52:39,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-02 10:52:39,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... + 7: [2022-12-02 10:52:39,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +46: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +46: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... +46: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... +46: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... +46: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +44: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +40: [2022-12-02 10:52:39,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +27: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +40: [2022-12-02 10:52:39,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:39,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +44: [2022-12-02 10:52:39,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +51: [2022-12-02 10:52:39,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +51: [2022-12-02 10:52:39,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 7: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +53: [2022-12-02 10:52:39,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +51: [2022-12-02 10:52:39,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +59: [2022-12-02 10:52:39,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-02 10:52:39,910] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 473 +51: [2022-12-02 10:52:39,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 3: [2022-12-02 10:52:39,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +51: [2022-12-02 10:52:39,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 3: [2022-12-02 10:52:39,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:39,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +12: [2022-12-02 10:52:39,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +51: [2022-12-02 10:52:39,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +63: [2022-12-02 10:52:39,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:39,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +63: [2022-12-02 10:52:39,915] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 507 +51: [2022-12-02 10:52:39,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +53: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +20: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +51: [2022-12-02 10:52:39,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +28: [2022-12-02 10:52:39,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +19: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +47: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +20: [2022-12-02 10:52:39,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +27: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +49: [2022-12-02 10:52:39,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +54: [2022-12-02 10:52:39,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +48: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +20: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +48: [2022-12-02 10:52:39,925] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 384 +60: [2022-12-02 10:52:39,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +14: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +15: [2022-12-02 10:52:39,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +20: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... +56: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +28: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:39,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 4: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +43: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... + 0: [2022-12-02 10:52:39,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:39,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:39,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +16: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +16: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +20: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +49: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_38-model_00-model_states.pt. +20: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +21: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +60: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +60: [2022-12-02 10:52:39,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +21: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +21: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +21: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +60: [2022-12-02 10:52:39,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +19: [2022-12-02 10:52:39,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +19: [2022-12-02 10:52:39,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +27: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +44: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +60: [2022-12-02 10:52:39,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +14: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +60: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +28: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +60: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +14: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:39,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:39,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:39,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +44: [2022-12-02 10:52:39,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +62: [2022-12-02 10:52:39,942] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 498 +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +44: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +44: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +44: [2022-12-02 10:52:39,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +27: [2022-12-02 10:52:39,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:39,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:39,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +12: [2022-12-02 10:52:39,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:39,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +12: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +36: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +12: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +12: [2022-12-02 10:52:39,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +53: [2022-12-02 10:52:39,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 7: [2022-12-02 10:52:39,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +53: [2022-12-02 10:52:39,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +45: [2022-12-02 10:52:39,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:39,950] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 361 +12: [2022-12-02 10:52:39,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:39,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +53: [2022-12-02 10:52:39,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +53: [2022-12-02 10:52:39,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +53: [2022-12-02 10:52:39,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +13: [2022-12-02 10:52:39,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +53: [2022-12-02 10:52:39,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +13: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:39,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:39,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +54: [2022-12-02 10:52:39,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +53: [2022-12-02 10:52:39,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +61: [2022-12-02 10:52:39,962] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 494 +53: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:39,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +15: [2022-12-02 10:52:39,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:39,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:39,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +13: [2022-12-02 10:52:39,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +54: [2022-12-02 10:52:39,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +58: [2022-12-02 10:52:39,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:39,968] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 465 +13: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +41: [2022-12-02 10:52:39,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:39,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +13: [2022-12-02 10:52:39,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +15: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +15: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +54: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +13: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +13: [2022-12-02 10:52:39,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +59: [2022-12-02 10:52:39,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +13: [2022-12-02 10:52:39,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:39,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +59: [2022-12-02 10:52:39,973] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 478 + 5: [2022-12-02 10:52:39,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +15: [2022-12-02 10:52:39,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:39,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:39,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +48: [2022-12-02 10:52:39,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-02 10:52:39,975] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 390 + 5: [2022-12-02 10:52:39,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +49: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +50: [2022-12-02 10:52:39,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-02 10:52:39,978] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 402 +49: [2022-12-02 10:52:39,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 9: [2022-12-02 10:52:39,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +49: [2022-12-02 10:52:39,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +49: [2022-12-02 10:52:39,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. +49: [2022-12-02 10:52:39,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt... +49: [2022-12-02 10:52:39,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_40-model_00-model_states.pt. + 9: [2022-12-02 10:52:39,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:39,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 5: [2022-12-02 10:52:39,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +62: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:39,991] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 496 +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +40: [2022-12-02 10:52:39,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:39,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:39,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:39,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:39,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:39,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,997] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:39,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:39,999] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:40,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:40,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:40,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:40,003] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:40,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:40,004] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,005] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +51: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +61: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,006] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 490 +18: [2022-12-02 10:52:40,006] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +21: [2022-12-02 10:52:40,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:40,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,007] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,008] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,009] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:40,011] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +18: [2022-12-02 10:52:40,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,012] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +45: [2022-12-02 10:52:40,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +59: [2022-12-02 10:52:40,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,014] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 367 +59: [2022-12-02 10:52:40,014] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 477 + 9: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +48: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. + 9: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +48: [2022-12-02 10:52:40,016] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 388 +29: [2022-12-02 10:52:40,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:40,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:40,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +58: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,018] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 467 + 9: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +20: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +38: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +29: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +38: [2022-12-02 10:52:40,020] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 304 +21: [2022-12-02 10:52:40,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-02 10:52:40,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +14: [2022-12-02 10:52:40,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +29: [2022-12-02 10:52:40,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:40,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:40,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:40,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:40,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +20: [2022-12-02 10:52:40,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +62: [2022-12-02 10:52:40,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:40,031] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 502 +33: [2022-12-02 10:52:40,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +28: [2022-12-02 10:52:40,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +33: [2022-12-02 10:52:40,032] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 270 + 0: [2022-12-02 10:52:40,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:40,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:40,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:40,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +62: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:40,035] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 497 +44: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +44: [2022-12-02 10:52:40,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +13: [2022-12-02 10:52:40,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +38: [2022-12-02 10:52:40,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. + 4: [2022-12-02 10:52:40,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +38: [2022-12-02 10:52:40,037] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 310 +14: [2022-12-02 10:52:40,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +50: [2022-12-02 10:52:40,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +28: [2022-12-02 10:52:40,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +50: [2022-12-02 10:52:40,040] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 406 +48: [2022-12-02 10:52:40,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +35: [2022-12-02 10:52:40,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +48: [2022-12-02 10:52:40,041] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 389 +61: [2022-12-02 10:52:40,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,041] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 488 + 0: [2022-12-02 10:52:40,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +35: [2022-12-02 10:52:40,041] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 286 + 0: [2022-12-02 10:52:40,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +63: [2022-12-02 10:52:40,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,043] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 505 + 0: [2022-12-02 10:52:40,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +14: [2022-12-02 10:52:40,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +21: [2022-12-02 10:52:40,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +63: [2022-12-02 10:52:40,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,046] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 510 +21: [2022-12-02 10:52:40,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-02 10:52:40,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +10: [2022-12-02 10:52:40,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +48: [2022-12-02 10:52:40,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-02 10:52:40,051] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 386 + 4: [2022-12-02 10:52:40,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +16: [2022-12-02 10:52:40,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +13: [2022-12-02 10:52:40,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +59: [2022-12-02 10:52:40,060] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-02 10:52:40,060] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 479 + 5: [2022-12-02 10:52:40,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:40,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +19: [2022-12-02 10:52:40,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +32: [2022-12-02 10:52:40,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +20: [2022-12-02 10:52:40,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,063] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +32: [2022-12-02 10:52:40,063] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 257 + 9: [2022-12-02 10:52:40,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +19: [2022-12-02 10:52:40,065] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +55: [2022-12-02 10:52:40,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +10: [2022-12-02 10:52:40,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +55: [2022-12-02 10:52:40,067] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 443 +59: [2022-12-02 10:52:40,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-02 10:52:40,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +10: [2022-12-02 10:52:40,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +59: [2022-12-02 10:52:40,068] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 474 +59: [2022-12-02 10:52:40,068] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 476 +13: [2022-12-02 10:52:40,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +35: [2022-12-02 10:52:40,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-02 10:52:40,069] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 282 +10: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +59: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +10: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +59: [2022-12-02 10:52:40,069] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 472 +13: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:40,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +14: [2022-12-02 10:52:40,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,066] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +58: [2022-12-02 10:52:40,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,070] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 468 +24: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +49: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +54: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +26: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:40,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:40,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +24: [2022-12-02 10:52:40,072] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +48: [2022-12-02 10:52:40,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +28: [2022-12-02 10:52:40,074] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +38: [2022-12-02 10:52:40,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +48: [2022-12-02 10:52:40,075] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 391 +38: [2022-12-02 10:52:40,075] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 306 +13: [2022-12-02 10:52:40,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,076] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:40,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +61: [2022-12-02 10:52:40,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,078] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 495 +18: [2022-12-02 10:52:40,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +28: [2022-12-02 10:52:40,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +61: [2022-12-02 10:52:40,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,078] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 493 +26: [2022-12-02 10:52:40,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:40,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +62: [2022-12-02 10:52:40,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:40,079] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 503 +26: [2022-12-02 10:52:40,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +28: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +35: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +26: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +26: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +50: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +33: [2022-12-02 10:52:40,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +35: [2022-12-02 10:52:40,084] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 287 +50: [2022-12-02 10:52:40,085] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 400 + 6: [2022-12-02 10:52:40,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +33: [2022-12-02 10:52:40,085] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 266 + 6: [2022-12-02 10:52:40,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +50: [2022-12-02 10:52:40,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-02 10:52:40,088] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 407 +34: [2022-12-02 10:52:40,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,089] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 364 +34: [2022-12-02 10:52:40,089] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 279 + 0: [2022-12-02 10:52:40,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +38: [2022-12-02 10:52:40,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +33: [2022-12-02 10:52:40,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,091] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 360 +38: [2022-12-02 10:52:40,091] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 305 +18: [2022-12-02 10:52:40,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +33: [2022-12-02 10:52:40,092] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 271 +34: [2022-12-02 10:52:40,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +35: [2022-12-02 10:52:40,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +34: [2022-12-02 10:52:40,094] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 277 +29: [2022-12-02 10:52:40,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +35: [2022-12-02 10:52:40,094] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 284 +29: [2022-12-02 10:52:40,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +18: [2022-12-02 10:52:40,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +58: [2022-12-02 10:52:40,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,095] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 469 + 2: [2022-12-02 10:52:40,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +59: [2022-12-02 10:52:40,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. +22: [2022-12-02 10:52:40,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +29: [2022-12-02 10:52:40,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +59: [2022-12-02 10:52:40,099] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 475 +22: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +13: [2022-12-02 10:52:40,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +63: [2022-12-02 10:52:40,103] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,104] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 504 + 6: [2022-12-02 10:52:40,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +34: [2022-12-02 10:52:40,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,106] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 492 +34: [2022-12-02 10:52:40,107] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 278 +62: [2022-12-02 10:52:40,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:40,101] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 499 +61: [2022-12-02 10:52:40,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,107] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 489 + 5: [2022-12-02 10:52:40,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:40,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +22: [2022-12-02 10:52:40,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:40,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:40,110] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:40,110] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 264 +22: [2022-12-02 10:52:40,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:40,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:40,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +22: [2022-12-02 10:52:40,112] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,114] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,115] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +35: [2022-12-02 10:52:40,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +18: [2022-12-02 10:52:40,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +35: [2022-12-02 10:52:40,117] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 280 +48: [2022-12-02 10:52:40,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-02 10:52:40,117] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 387 +18: [2022-12-02 10:52:40,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +50: [2022-12-02 10:52:40,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-02 10:52:40,119] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 405 +38: [2022-12-02 10:52:40,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-02 10:52:40,122] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 309 +11: [2022-12-02 10:52:40,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:40,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:40,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +11: [2022-12-02 10:52:40,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +38: [2022-12-02 10:52:40,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. + 2: [2022-12-02 10:52:40,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +38: [2022-12-02 10:52:40,128] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 311 +50: [2022-12-02 10:52:40,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-02 10:52:40,130] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 403 +10: [2022-12-02 10:52:40,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +63: [2022-12-02 10:52:40,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,131] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 508 +34: [2022-12-02 10:52:40,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +18: [2022-12-02 10:52:40,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +34: [2022-12-02 10:52:40,132] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 272 +29: [2022-12-02 10:52:40,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +63: [2022-12-02 10:52:40,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. +18: [2022-12-02 10:52:40,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +63: [2022-12-02 10:52:40,134] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 509 +29: [2022-12-02 10:52:40,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +45: [2022-12-02 10:52:40,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. +10: [2022-12-02 10:52:40,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +45: [2022-12-02 10:52:40,136] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 365 +18: [2022-12-02 10:52:40,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +38: [2022-12-02 10:52:40,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +31: [2022-12-02 10:52:40,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:40,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +33: [2022-12-02 10:52:40,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +38: [2022-12-02 10:52:40,141] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 307 +33: [2022-12-02 10:52:40,141] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 265 +31: [2022-12-02 10:52:40,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:40,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:40,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:40,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:40,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +31: [2022-12-02 10:52:40,142] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt... +48: [2022-12-02 10:52:40,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +32: [2022-12-02 10:52:40,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. +48: [2022-12-02 10:52:40,143] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 385 +58: [2022-12-02 10:52:40,143] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 464 +45: [2022-12-02 10:52:40,143] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 363 +29: [2022-12-02 10:52:40,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +32: [2022-12-02 10:52:40,143] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 258 +29: [2022-12-02 10:52:40,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +34: [2022-12-02 10:52:40,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +29: [2022-12-02 10:52:40,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,144] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +34: [2022-12-02 10:52:40,145] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 274 +26: [2022-12-02 10:52:40,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +32: [2022-12-02 10:52:40,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-02 10:52:40,151] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 259 +24: [2022-12-02 10:52:40,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +55: [2022-12-02 10:52:40,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-02 10:52:40,154] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 440 +35: [2022-12-02 10:52:40,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,155] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 511 +35: [2022-12-02 10:52:40,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-02 10:52:40,155] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 283 +35: [2022-12-02 10:52:40,156] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 285 + 2: [2022-12-02 10:52:40,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +35: [2022-12-02 10:52:40,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-02 10:52:40,157] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 281 +10: [2022-12-02 10:52:40,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +55: [2022-12-02 10:52:40,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +55: [2022-12-02 10:52:40,164] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 442 + 2: [2022-12-02 10:52:40,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +61: [2022-12-02 10:52:40,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-02 10:52:40,166] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 491 +33: [2022-12-02 10:52:40,168] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. +33: [2022-12-02 10:52:40,168] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 269 +26: [2022-12-02 10:52:40,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +26: [2022-12-02 10:52:40,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +50: [2022-12-02 10:52:40,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. +50: [2022-12-02 10:52:40,170] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 401 +10: [2022-12-02 10:52:40,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +32: [2022-12-02 10:52:40,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-02 10:52:40,178] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 260 +24: [2022-12-02 10:52:40,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +34: [2022-12-02 10:52:40,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +33: [2022-12-02 10:52:40,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +34: [2022-12-02 10:52:40,183] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 276 +33: [2022-12-02 10:52:40,183] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 267 +26: [2022-12-02 10:52:40,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +45: [2022-12-02 10:52:40,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,186] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 362 +50: [2022-12-02 10:52:40,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +22: [2022-12-02 10:52:40,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +50: [2022-12-02 10:52:40,188] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 404 +22: [2022-12-02 10:52:40,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +55: [2022-12-02 10:52:40,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-02 10:52:40,191] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 445 +22: [2022-12-02 10:52:40,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +22: [2022-12-02 10:52:40,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +24: [2022-12-02 10:52:40,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +10: [2022-12-02 10:52:40,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +32: [2022-12-02 10:52:40,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-02 10:52:40,201] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 261 +32: [2022-12-02 10:52:40,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-02 10:52:40,202] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 263 +26: [2022-12-02 10:52:40,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +58: [2022-12-02 10:52:40,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,208] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 466 +55: [2022-12-02 10:52:40,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +26: [2022-12-02 10:52:40,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +55: [2022-12-02 10:52:40,210] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 441 +55: [2022-12-02 10:52:40,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-02 10:52:40,211] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 444 +11: [2022-12-02 10:52:40,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +11: [2022-12-02 10:52:40,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +32: [2022-12-02 10:52:40,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +31: [2022-12-02 10:52:40,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +32: [2022-12-02 10:52:40,218] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 256 +31: [2022-12-02 10:52:40,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +31: [2022-12-02 10:52:40,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_17-model_00-model_states.pt. +58: [2022-12-02 10:52:40,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,227] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 471 +22: [2022-12-02 10:52:40,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +33: [2022-12-02 10:52:40,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +22: [2022-12-02 10:52:40,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +33: [2022-12-02 10:52:40,229] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 268 +22: [2022-12-02 10:52:40,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:40,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +22: [2022-12-02 10:52:40,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:40,236] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 317 +11: [2022-12-02 10:52:40,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +52: [2022-12-02 10:52:40,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-02 10:52:40,246] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 422 +55: [2022-12-02 10:52:40,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-02 10:52:40,247] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 447 +11: [2022-12-02 10:52:40,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +45: [2022-12-02 10:52:40,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-02 10:52:40,253] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 366 +32: [2022-12-02 10:52:40,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-02 10:52:40,254] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 262 +31: [2022-12-02 10:52:40,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +62: [2022-12-02 10:52:40,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:40,259] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 500 +58: [2022-12-02 10:52:40,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-02 10:52:40,260] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 470 +31: [2022-12-02 10:52:40,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +46: [2022-12-02 10:52:40,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,267] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 371 +42: [2022-12-02 10:52:40,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-02 10:52:40,276] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 341 +38: [2022-12-02 10:52:40,299] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-02 10:52:40,300] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 308 +43: [2022-12-02 10:52:40,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-02 10:52:40,307] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 347 +39: [2022-12-02 10:52:40,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-02 10:52:40,310] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 313 + 8: [2022-12-02 10:52:40,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +47: [2022-12-02 10:52:40,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-02 10:52:40,325] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 377 + 8: [2022-12-02 10:52:40,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,327] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +52: [2022-12-02 10:52:40,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-02 10:52:40,331] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 417 +57: [2022-12-02 10:52:40,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-02 10:52:40,342] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 458 +39: [2022-12-02 10:52:40,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-02 10:52:40,347] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 315 +36: [2022-12-02 10:52:40,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-02 10:52:40,357] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 289 +55: [2022-12-02 10:52:40,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-02 10:52:40,359] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 446 +46: [2022-12-02 10:52:40,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 374 +42: [2022-12-02 10:52:40,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-02 10:52:40,361] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 337 +43: [2022-12-02 10:52:40,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-02 10:52:40,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 350 +42: [2022-12-02 10:52:40,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-02 10:52:40,369] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 342 +37: [2022-12-02 10:52:40,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-02 10:52:40,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 303 +51: [2022-12-02 10:52:40,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:40,372] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 411 +39: [2022-12-02 10:52:40,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +36: [2022-12-02 10:52:40,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +39: [2022-12-02 10:52:40,376] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 316 +36: [2022-12-02 10:52:40,377] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 290 +40: [2022-12-02 10:52:40,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-02 10:52:40,378] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 322 +17: [2022-12-02 10:52:40,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +47: [2022-12-02 10:52:40,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +56: [2022-12-02 10:52:40,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +47: [2022-12-02 10:52:40,385] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 378 +56: [2022-12-02 10:52:40,385] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 448 +42: [2022-12-02 10:52:40,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +41: [2022-12-02 10:52:40,386] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. +42: [2022-12-02 10:52:40,387] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 340 +41: [2022-12-02 10:52:40,387] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 330 +52: [2022-12-02 10:52:40,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-02 10:52:40,387] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 423 + 8: [2022-12-02 10:52:40,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +52: [2022-12-02 10:52:40,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +17: [2022-12-02 10:52:40,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +52: [2022-12-02 10:52:40,388] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 419 +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,390] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +34: [2022-12-02 10:52:40,392] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-02 10:52:40,392] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 273 +56: [2022-12-02 10:52:40,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-02 10:52:40,393] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 455 +52: [2022-12-02 10:52:40,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-02 10:52:40,396] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 416 + 3: [2022-12-02 10:52:40,396] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +46: [2022-12-02 10:52:40,399] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,400] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 368 +63: [2022-12-02 10:52:40,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-02 10:52:40,400] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 506 +39: [2022-12-02 10:52:40,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. + 3: [2022-12-02 10:52:40,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:40,401] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 319 +30: [2022-12-02 10:52:40,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +52: [2022-12-02 10:52:40,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-02 10:52:40,405] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 418 + 7: [2022-12-02 10:52:40,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,407] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +52: [2022-12-02 10:52:40,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-02 10:52:40,408] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 421 +30: [2022-12-02 10:52:40,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +41: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. + 7: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +41: [2022-12-02 10:52:40,410] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 331 + 3: [2022-12-02 10:52:40,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:40,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. + 7: [2022-12-02 10:52:40,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +43: [2022-12-02 10:52:40,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +57: [2022-12-02 10:52:40,411] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +39: [2022-12-02 10:52:40,411] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 312 +43: [2022-12-02 10:52:40,411] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 346 +57: [2022-12-02 10:52:40,411] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 463 +43: [2022-12-02 10:52:40,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +43: [2022-12-02 10:52:40,412] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 348 +37: [2022-12-02 10:52:40,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +30: [2022-12-02 10:52:40,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:40,413] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:40,414] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 298 + 0: [2022-12-02 10:52:40,414] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +57: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +27: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +57: [2022-12-02 10:52:40,416] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 456 +30: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +46: [2022-12-02 10:52:40,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. + 8: [2022-12-02 10:52:40,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +46: [2022-12-02 10:52:40,420] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 375 + 8: [2022-12-02 10:52:40,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:40,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +62: [2022-12-02 10:52:40,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +62: [2022-12-02 10:52:40,422] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 501 + 7: [2022-12-02 10:52:40,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:40,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +27: [2022-12-02 10:52:40,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +39: [2022-12-02 10:52:40,423] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 318 + 7: [2022-12-02 10:52:40,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +47: [2022-12-02 10:52:40,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. + 0: [2022-12-02 10:52:40,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +47: [2022-12-02 10:52:40,425] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 379 +34: [2022-12-02 10:52:40,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-02 10:52:40,427] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 275 +46: [2022-12-02 10:52:40,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,428] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 372 +47: [2022-12-02 10:52:40,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-02 10:52:40,430] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 383 +27: [2022-12-02 10:52:40,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +47: [2022-12-02 10:52:40,434] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-02 10:52:40,435] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 381 + 0: [2022-12-02 10:52:40,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:40,437] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. + 1: [2022-12-02 10:52:40,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:40,438] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 301 +39: [2022-12-02 10:52:40,438] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-02 10:52:40,439] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 314 +51: [2022-12-02 10:52:40,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:40,439] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 409 + 1: [2022-12-02 10:52:40,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,440] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:40,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,441] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,441] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 437 +37: [2022-12-02 10:52:40,441] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 297 +51: [2022-12-02 10:52:40,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:40,443] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 415 +42: [2022-12-02 10:52:40,448] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. + 1: [2022-12-02 10:52:40,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +40: [2022-12-02 10:52:40,449] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. + 1: [2022-12-02 10:52:40,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +42: [2022-12-02 10:52:40,449] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 343 + 1: [2022-12-02 10:52:40,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +40: [2022-12-02 10:52:40,449] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 325 +53: [2022-12-02 10:52:40,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +42: [2022-12-02 10:52:40,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +36: [2022-12-02 10:52:40,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +53: [2022-12-02 10:52:40,456] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 428 +42: [2022-12-02 10:52:40,456] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 338 +36: [2022-12-02 10:52:40,457] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 295 +36: [2022-12-02 10:52:40,458] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-02 10:52:40,459] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 291 +17: [2022-12-02 10:52:40,461] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,461] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +46: [2022-12-02 10:52:40,462] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,462] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 373 +36: [2022-12-02 10:52:40,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +47: [2022-12-02 10:52:40,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +36: [2022-12-02 10:52:40,464] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 288 + 8: [2022-12-02 10:52:40,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,464] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +47: [2022-12-02 10:52:40,464] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 380 +17: [2022-12-02 10:52:40,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,465] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,466] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +36: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +36: [2022-12-02 10:52:40,468] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 294 +51: [2022-12-02 10:52:40,471] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:40,472] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 412 +57: [2022-12-02 10:52:40,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +49: [2022-12-02 10:52:40,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +57: [2022-12-02 10:52:40,474] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 459 +49: [2022-12-02 10:52:40,475] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 396 +23: [2022-12-02 10:52:40,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,475] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,479] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:40,479] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +56: [2022-12-02 10:52:40,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-02 10:52:40,480] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 451 +27: [2022-12-02 10:52:40,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,482] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +43: [2022-12-02 10:52:40,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-02 10:52:40,485] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 345 +41: [2022-12-02 10:52:40,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-02 10:52:40,486] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 334 + 7: [2022-12-02 10:52:40,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +56: [2022-12-02 10:52:40,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-02 10:52:40,488] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 453 + 3: [2022-12-02 10:52:40,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,491] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +46: [2022-12-02 10:52:40,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,494] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 370 +40: [2022-12-02 10:52:40,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +42: [2022-12-02 10:52:40,494] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +40: [2022-12-02 10:52:40,495] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 324 +42: [2022-12-02 10:52:40,495] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 339 +42: [2022-12-02 10:52:40,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. + 0: [2022-12-02 10:52:40,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +42: [2022-12-02 10:52:40,496] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 336 +17: [2022-12-02 10:52:40,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:40,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,496] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +44: [2022-12-02 10:52:40,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-02 10:52:40,499] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 358 +12: [2022-12-02 10:52:40,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:40,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +40: [2022-12-02 10:52:40,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +12: [2022-12-02 10:52:40,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +40: [2022-12-02 10:52:40,501] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 326 +12: [2022-12-02 10:52:40,500] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,500] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,501] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +17: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-02 10:52:40,503] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 427 +44: [2022-12-02 10:52:40,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-02 10:52:40,503] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 357 +57: [2022-12-02 10:52:40,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-02 10:52:40,505] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 462 +17: [2022-12-02 10:52:40,505] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +17: [2022-12-02 10:52:40,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:40,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +56: [2022-12-02 10:52:40,510] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +16: [2022-12-02 10:52:40,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +56: [2022-12-02 10:52:40,511] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 449 +16: [2022-12-02 10:52:40,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:40,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +43: [2022-12-02 10:52:40,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-02 10:52:40,513] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 344 +57: [2022-12-02 10:52:40,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +17: [2022-12-02 10:52:40,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +57: [2022-12-02 10:52:40,513] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 457 +17: [2022-12-02 10:52:40,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +36: [2022-12-02 10:52:40,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-02 10:52:40,516] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 292 + 3: [2022-12-02 10:52:40,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 3: [2022-12-02 10:52:40,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +40: [2022-12-02 10:52:40,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +27: [2022-12-02 10:52:40,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +47: [2022-12-02 10:52:40,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +40: [2022-12-02 10:52:40,519] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 323 +47: [2022-12-02 10:52:40,519] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 376 +30: [2022-12-02 10:52:40,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:40,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +60: [2022-12-02 10:52:40,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +60: [2022-12-02 10:52:40,521] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 480 +41: [2022-12-02 10:52:40,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-02 10:52:40,521] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 333 +36: [2022-12-02 10:52:40,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +30: [2022-12-02 10:52:40,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +36: [2022-12-02 10:52:40,522] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 293 + 7: [2022-12-02 10:52:40,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +46: [2022-12-02 10:52:40,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-02 10:52:40,525] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 369 +41: [2022-12-02 10:52:40,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. + 7: [2022-12-02 10:52:40,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +41: [2022-12-02 10:52:40,526] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 329 +51: [2022-12-02 10:52:40,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +30: [2022-12-02 10:52:40,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +51: [2022-12-02 10:52:40,528] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 408 + 0: [2022-12-02 10:52:40,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +53: [2022-12-02 10:52:40,531] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 430 +20: [2022-12-02 10:52:40,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 7: [2022-12-02 10:52:40,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +60: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-02 10:52:40,533] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 485 +44: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +44: [2022-12-02 10:52:40,533] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 359 + 3: [2022-12-02 10:52:40,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +52: [2022-12-02 10:52:40,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +40: [2022-12-02 10:52:40,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. + 1: [2022-12-02 10:52:40,536] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +52: [2022-12-02 10:52:40,537] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 420 + 1: [2022-12-02 10:52:40,537] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +40: [2022-12-02 10:52:40,537] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 321 + 1: [2022-12-02 10:52:40,537] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +37: [2022-12-02 10:52:40,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. + 7: [2022-12-02 10:52:40,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +20: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +37: [2022-12-02 10:52:40,543] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 300 +20: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +51: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +37: [2022-12-02 10:52:40,543] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 296 +51: [2022-12-02 10:52:40,543] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 410 +51: [2022-12-02 10:52:40,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:40,544] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 414 +20: [2022-12-02 10:52:40,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +43: [2022-12-02 10:52:40,547] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. + 9: [2022-12-02 10:52:40,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +43: [2022-12-02 10:52:40,548] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 351 + 1: [2022-12-02 10:52:40,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +40: [2022-12-02 10:52:40,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +43: [2022-12-02 10:52:40,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +57: [2022-12-02 10:52:40,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +40: [2022-12-02 10:52:40,549] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 327 +57: [2022-12-02 10:52:40,549] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 461 + 9: [2022-12-02 10:52:40,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +43: [2022-12-02 10:52:40,549] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 349 +49: [2022-12-02 10:52:40,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. + 7: [2022-12-02 10:52:40,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:40,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +49: [2022-12-02 10:52:40,550] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-02 10:52:40,550] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 393 +49: [2022-12-02 10:52:40,550] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 399 +37: [2022-12-02 10:52:40,552] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-02 10:52:40,553] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 299 + 9: [2022-12-02 10:52:40,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +56: [2022-12-02 10:52:40,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +23: [2022-12-02 10:52:40,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +56: [2022-12-02 10:52:40,556] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 454 +23: [2022-12-02 10:52:40,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +23: [2022-12-02 10:52:40,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,556] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 425 +15: [2022-12-02 10:52:40,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +44: [2022-12-02 10:52:40,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +15: [2022-12-02 10:52:40,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +44: [2022-12-02 10:52:40,559] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 352 +15: [2022-12-02 10:52:40,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:40,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +30: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +27: [2022-12-02 10:52:40,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:40,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +54: [2022-12-02 10:52:40,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +60: [2022-12-02 10:52:40,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. + 3: [2022-12-02 10:52:40,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +60: [2022-12-02 10:52:40,565] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 482 +54: [2022-12-02 10:52:40,565] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 436 +27: [2022-12-02 10:52:40,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:40,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +44: [2022-12-02 10:52:40,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. + 3: [2022-12-02 10:52:40,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:40,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +44: [2022-12-02 10:52:40,567] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 354 + 3: [2022-12-02 10:52:40,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:40,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:40,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:40,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:40,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:40,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:40,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +51: [2022-12-02 10:52:40,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-02 10:52:40,571] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 413 + 3: [2022-12-02 10:52:40,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +60: [2022-12-02 10:52:40,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-02 10:52:40,571] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 486 +10: [2022-12-02 10:52:40,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +25: [2022-12-02 10:52:40,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +13: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +27: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +49: [2022-12-02 10:52:40,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-02 10:52:40,574] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 392 +54: [2022-12-02 10:52:40,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,575] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 434 +12: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,577] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +25: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,577] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,578] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,578] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,579] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,581] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:40,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,582] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 0: [2022-12-02 10:52:40,582] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,583] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +21: [2022-12-02 10:52:40,585] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +25: [2022-12-02 10:52:40,586] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,587] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,588] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,589] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,589] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-02 10:52:40,591] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 424 +19: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +60: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. + 6: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +60: [2022-12-02 10:52:40,591] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 481 +16: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +60: [2022-12-02 10:52:40,591] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 487 +16: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +23: [2022-12-02 10:52:40,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +49: [2022-12-02 10:52:40,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-02 10:52:40,594] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 395 + 6: [2022-12-02 10:52:40,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +23: [2022-12-02 10:52:40,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,595] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +44: [2022-12-02 10:52:40,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +23: [2022-12-02 10:52:40,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:40,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +44: [2022-12-02 10:52:40,597] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 353 +23: [2022-12-02 10:52:40,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:40,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:40,597] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +60: [2022-12-02 10:52:40,598] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +24: [2022-12-02 10:52:40,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +60: [2022-12-02 10:52:40,598] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 484 +24: [2022-12-02 10:52:40,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,599] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +24: [2022-12-02 10:52:40,600] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +19: [2022-12-02 10:52:40,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +12: [2022-12-02 10:52:40,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:40,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:40,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:40,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +44: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +44: [2022-12-02 10:52:40,616] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 355 +56: [2022-12-02 10:52:40,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +40: [2022-12-02 10:52:40,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +56: [2022-12-02 10:52:40,616] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 452 + 2: [2022-12-02 10:52:40,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +40: [2022-12-02 10:52:40,617] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 320 +12: [2022-12-02 10:52:40,613] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +37: [2022-12-02 10:52:40,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +20: [2022-12-02 10:52:40,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +37: [2022-12-02 10:52:40,616] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 302 +20: [2022-12-02 10:52:40,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:40,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +47: [2022-12-02 10:52:40,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +20: [2022-12-02 10:52:40,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:40,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +47: [2022-12-02 10:52:40,622] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 382 +14: [2022-12-02 10:52:40,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +12: [2022-12-02 10:52:40,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +54: [2022-12-02 10:52:40,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,623] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 433 +54: [2022-12-02 10:52:40,623] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 435 + 9: [2022-12-02 10:52:40,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +16: [2022-12-02 10:52:40,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +20: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:40,630] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 432 +54: [2022-12-02 10:52:40,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-02 10:52:40,630] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 438 + 2: [2022-12-02 10:52:40,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +54: [2022-12-02 10:52:40,631] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 439 + 2: [2022-12-02 10:52:40,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +16: [2022-12-02 10:52:40,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:40,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:40,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +15: [2022-12-02 10:52:40,634] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,636] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +49: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +14: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +49: [2022-12-02 10:52:40,640] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 398 +29: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +41: [2022-12-02 10:52:40,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +29: [2022-12-02 10:52:40,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +41: [2022-12-02 10:52:40,651] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 328 +29: [2022-12-02 10:52:40,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,651] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +41: [2022-12-02 10:52:40,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +29: [2022-12-02 10:52:40,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +29: [2022-12-02 10:52:40,652] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +41: [2022-12-02 10:52:40,652] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 335 + 9: [2022-12-02 10:52:40,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:40,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +20: [2022-12-02 10:52:40,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +13: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,659] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 429 +28: [2022-12-02 10:52:40,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. +53: [2022-12-02 10:52:40,660] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 431 + 5: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +13: [2022-12-02 10:52:40,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:40,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:40,673] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +49: [2022-12-02 10:52:40,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +24: [2022-12-02 10:52:40,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +49: [2022-12-02 10:52:40,675] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 394 +24: [2022-12-02 10:52:40,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +20: [2022-12-02 10:52:40,677] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +44: [2022-12-02 10:52:40,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-02 10:52:40,678] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 356 +10: [2022-12-02 10:52:40,678] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,679] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,680] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,683] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:40,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +15: [2022-12-02 10:52:40,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 5: [2022-12-02 10:52:40,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:40,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:40,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +49: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +15: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:40,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +49: [2022-12-02 10:52:40,695] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 397 +11: [2022-12-02 10:52:40,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +10: [2022-12-02 10:52:40,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +10: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +11: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +25: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:40,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 9: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +25: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 9: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:40,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:40,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +41: [2022-12-02 10:52:40,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +11: [2022-12-02 10:52:40,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +41: [2022-12-02 10:52:40,709] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 332 + 5: [2022-12-02 10:52:40,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:40,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +21: [2022-12-02 10:52:40,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:40,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +24: [2022-12-02 10:52:40,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:40,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:40,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 6: [2022-12-02 10:52:40,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +14: [2022-12-02 10:52:40,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +28: [2022-12-02 10:52:40,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +19: [2022-12-02 10:52:40,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:40,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +28: [2022-12-02 10:52:40,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:40,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +18: [2022-12-02 10:52:40,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +11: [2022-12-02 10:52:40,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:40,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +56: [2022-12-02 10:52:40,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-02 10:52:40,755] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 450 +14: [2022-12-02 10:52:40,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 2: [2022-12-02 10:52:40,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +57: [2022-12-02 10:52:40,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +14: [2022-12-02 10:52:40,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +57: [2022-12-02 10:52:40,765] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 460 + 2: [2022-12-02 10:52:40,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:40,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +14: [2022-12-02 10:52:40,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +60: [2022-12-02 10:52:40,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-02 10:52:40,770] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 483 +14: [2022-12-02 10:52:40,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:40,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +29: [2022-12-02 10:52:40,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:40,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +18: [2022-12-02 10:52:40,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +31: [2022-12-02 10:52:40,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +53: [2022-12-02 10:52:40,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +26: [2022-12-02 10:52:40,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +53: [2022-12-02 10:52:40,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 426 +18: [2022-12-02 10:52:40,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:40,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. + 4: [2022-12-02 10:52:40,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +26: [2022-12-02 10:52:40,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +26: [2022-12-02 10:52:40,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:40,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +22: [2022-12-02 10:52:40,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt... +31: [2022-12-02 10:52:40,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:40,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:40,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +22: [2022-12-02 10:52:40,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_18-model_00-model_states.pt. +30: [2022-12-02 10:52:40,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:40,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:40,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:40,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:40,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 8: [2022-12-02 10:52:40,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:40,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:40,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:40,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:40,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:41,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,020] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,059] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,061] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +30: [2022-12-02 10:52:41,064] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +30: [2022-12-02 10:52:41,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,068] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,069] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:41,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,072] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,075] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:41,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,109] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:41,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +17: [2022-12-02 10:52:41,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,131] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,132] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,140] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +12: [2022-12-02 10:52:41,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +12: [2022-12-02 10:52:41,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,166] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,230] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +23: [2022-12-02 10:52:41,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +23: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +28: [2022-12-02 10:52:41,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,270] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,272] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +10: [2022-12-02 10:52:41,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +16: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +10: [2022-12-02 10:52:41,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:41,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:41,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:41,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +20: [2022-12-02 10:52:41,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +16: [2022-12-02 10:52:41,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,297] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,300] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +24: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,303] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,304] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,307] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:41,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +27: [2022-12-02 10:52:41,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +14: [2022-12-02 10:52:41,326] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,354] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,356] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,357] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +28: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:41,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,360] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,362] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,363] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,364] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +13: [2022-12-02 10:52:41,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:41,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +21: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +27: [2022-12-02 10:52:41,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +14: [2022-12-02 10:52:41,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,374] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +24: [2022-12-02 10:52:41,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +15: [2022-12-02 10:52:41,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +20: [2022-12-02 10:52:41,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +15: [2022-12-02 10:52:41,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +13: [2022-12-02 10:52:41,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,390] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +25: [2022-12-02 10:52:41,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,392] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +25: [2022-12-02 10:52:41,393] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:41,393] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:41,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:41,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:41,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +29: [2022-12-02 10:52:41,394] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,394] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,395] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,396] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,397] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,398] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,399] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,406] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,408] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,409] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +21: [2022-12-02 10:52:41,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,411] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:41,412] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,416] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,420] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +26: [2022-12-02 10:52:41,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,433] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,434] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:41,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:41,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:41,438] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:41,439] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +31: [2022-12-02 10:52:41,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,440] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:41,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +19: [2022-12-02 10:52:41,441] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,442] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,444] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,445] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,448] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,449] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,452] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +26: [2022-12-02 10:52:41,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,453] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,454] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,455] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,456] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,464] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +31: [2022-12-02 10:52:41,466] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,467] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,468] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,469] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,470] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,477] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,478] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,481] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,482] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:41,483] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,484] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,485] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +18: [2022-12-02 10:52:41,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,490] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +11: [2022-12-02 10:52:41,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,492] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:41,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:41,493] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:41,495] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:41,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +22: [2022-12-02 10:52:41,496] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt... +18: [2022-12-02 10:52:41,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:41,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:41,497] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:41,498] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,499] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,503] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,504] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,512] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,513] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +11: [2022-12-02 10:52:41,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +29: [2022-12-02 10:52:41,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,522] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:41,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,526] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,548] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. + 4: [2022-12-02 10:52:41,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +19: [2022-12-02 10:52:41,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:41,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +22: [2022-12-02 10:52:41,575] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_19-model_00-model_states.pt. +17: [2022-12-02 10:52:41,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,587] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,595] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,596] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,598] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,601] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,604] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 8: [2022-12-02 10:52:41,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 1: [2022-12-02 10:52:41,605] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,607] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,608] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +17: [2022-12-02 10:52:41,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,609] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,610] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:41,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,611] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,612] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +12: [2022-12-02 10:52:41,614] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +23: [2022-12-02 10:52:41,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,616] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,618] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:41,619] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,634] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,637] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,648] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +10: [2022-12-02 10:52:41,649] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +49: [2022-12-02 10:52:41,662] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 399 + 1: [2022-12-02 10:52:41,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +49: [2022-12-02 10:52:41,673] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 397 +12: [2022-12-02 10:52:41,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +49: [2022-12-02 10:52:41,675] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 396 + 3: [2022-12-02 10:52:41,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +49: [2022-12-02 10:52:41,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 394 +23: [2022-12-02 10:52:41,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +49: [2022-12-02 10:52:41,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 398 +49: [2022-12-02 10:52:41,684] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 395 + 0: [2022-12-02 10:52:41,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +49: [2022-12-02 10:52:41,686] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 392 +12: [2022-12-02 10:52:41,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +49: [2022-12-02 10:52:41,687] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 393 + 1: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 1: [2022-12-02 10:52:41,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +12: [2022-12-02 10:52:41,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 8: [2022-12-02 10:52:41,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: [2022-12-02 10:52:41,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:41,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:41,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 7: [2022-12-02 10:52:41,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +35: [2022-12-02 10:52:41,728] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 284 + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +32: [2022-12-02 10:52:41,731] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 260 +10: [2022-12-02 10:52:41,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +33: [2022-12-02 10:52:41,735] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 265 +44: [2022-12-02 10:52:41,743] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 352 +40: [2022-12-02 10:52:41,745] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 327 +32: [2022-12-02 10:52:41,747] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 263 +40: [2022-12-02 10:52:41,748] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 325 +33: [2022-12-02 10:52:41,755] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 268 +33: [2022-12-02 10:52:41,756] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 266 +40: [2022-12-02 10:52:41,758] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 323 +55: [2022-12-02 10:52:41,763] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 447 +55: [2022-12-02 10:52:41,765] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 445 +30: [2022-12-02 10:52:41,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +55: [2022-12-02 10:52:41,768] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 441 +30: [2022-12-02 10:52:41,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +33: [2022-12-02 10:52:41,770] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 271 +55: [2022-12-02 10:52:41,770] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 440 +55: [2022-12-02 10:52:41,771] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 446 +44: [2022-12-02 10:52:41,772] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 355 +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +40: [2022-12-02 10:52:41,773] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 322 +55: [2022-12-02 10:52:41,773] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 443 + 9: [2022-12-02 10:52:41,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +40: [2022-12-02 10:52:41,774] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 324 +33: [2022-12-02 10:52:41,774] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 264 +30: [2022-12-02 10:52:41,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 0: > using checkpoint value 0.0002 for learning rate + 0: > using checkpoint value 2e-05 for minimum learning rate + 0: > using checkpoint value 377930 for warmup iterations + 0: > using checkpoint value 37792969 for total number of iterations + 0: > using checkpoint value cosine for decay style +33: [2022-12-02 10:52:41,775] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 270 +44: [2022-12-02 10:52:41,776] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 353 +30: [2022-12-02 10:52:41,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +33: [2022-12-02 10:52:41,778] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 267 +39: [2022-12-02 10:52:41,778] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 318 +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +44: [2022-12-02 10:52:41,780] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 356 +55: [2022-12-02 10:52:41,781] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 444 +44: [2022-12-02 10:52:41,781] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 357 +44: [2022-12-02 10:52:41,781] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 358 +55: [2022-12-02 10:52:41,781] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 442 +40: [2022-12-02 10:52:41,782] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 326 +16: [2022-12-02 10:52:41,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +32: [2022-12-02 10:52:41,783] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 262 +16: [2022-12-02 10:52:41,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +42: [2022-12-02 10:52:41,784] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 336 +16: [2022-12-02 10:52:41,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +32: [2022-12-02 10:52:41,786] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 261 +30: [2022-12-02 10:52:41,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +44: [2022-12-02 10:52:41,788] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 359 +40: [2022-12-02 10:52:41,788] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 320 +39: [2022-12-02 10:52:41,789] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 317 +13: [2022-12-02 10:52:41,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +44: [2022-12-02 10:52:41,790] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 354 +13: [2022-12-02 10:52:41,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +39: [2022-12-02 10:52:41,791] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 319 +13: [2022-12-02 10:52:41,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 3: [2022-12-02 10:52:41,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +40: [2022-12-02 10:52:41,797] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 321 +33: [2022-12-02 10:52:41,800] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 269 +42: [2022-12-02 10:52:41,800] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 342 +39: [2022-12-02 10:52:41,801] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 316 +42: [2022-12-02 10:52:41,801] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 341 +32: [2022-12-02 10:52:41,802] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 256 +32: [2022-12-02 10:52:41,802] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 257 +42: [2022-12-02 10:52:41,802] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 337 +32: [2022-12-02 10:52:41,803] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 258 + 9: [2022-12-02 10:52:41,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +39: [2022-12-02 10:52:41,805] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 313 +42: [2022-12-02 10:52:41,805] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 343 + 9: [2022-12-02 10:52:41,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 9: [2022-12-02 10:52:41,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:41,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +39: [2022-12-02 10:52:41,808] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 314 +32: [2022-12-02 10:52:41,808] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 259 + 3: [2022-12-02 10:52:41,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-12-02 10:52:41,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-12-02 10:52:41,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-12-02 10:52:41,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-02 10:52:41,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:41,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +42: [2022-12-02 10:52:41,814] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 338 +42: [2022-12-02 10:52:41,814] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 340 + 3: [2022-12-02 10:52:41,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +39: [2022-12-02 10:52:41,816] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 312 + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:41,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +35: [2022-12-02 10:52:41,818] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 285 +39: [2022-12-02 10:52:41,819] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 315 + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-12-02 10:52:41,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +42: [2022-12-02 10:52:41,822] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 339 +35: [2022-12-02 10:52:41,827] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 281 +35: [2022-12-02 10:52:41,828] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 286 +14: [2022-12-02 10:52:41,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +35: [2022-12-02 10:52:41,831] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 287 +14: [2022-12-02 10:52:41,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +35: [2022-12-02 10:52:41,834] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 280 +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +41: [2022-12-02 10:52:41,835] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 328 +35: [2022-12-02 10:52:41,836] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 282 +14: [2022-12-02 10:52:41,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +35: [2022-12-02 10:52:41,843] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 283 +25: [2022-12-02 10:52:41,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +30: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +41: [2022-12-02 10:52:41,841] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 335 +14: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:41,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:41,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-12-02 10:52:41,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:41,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +13: [2022-12-02 10:52:41,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +16: [2022-12-02 10:52:41,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:41,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +13: [2022-12-02 10:52:41,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +41: [2022-12-02 10:52:41,884] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 329 + 6: [2022-12-02 10:52:41,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +41: [2022-12-02 10:52:41,885] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 334 + 6: [2022-12-02 10:52:41,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +30: [2022-12-02 10:52:41,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +41: [2022-12-02 10:52:41,892] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 330 +24: [2022-12-02 10:52:41,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +24: [2022-12-02 10:52:41,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +41: [2022-12-02 10:52:41,900] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 332 +20: [2022-12-02 10:52:41,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +41: [2022-12-02 10:52:41,900] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 331 +20: [2022-12-02 10:52:41,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +20: [2022-12-02 10:52:41,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +41: [2022-12-02 10:52:41,907] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 333 +62: [2022-12-02 10:52:41,909] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 496 +28: [2022-12-02 10:52:41,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +62: [2022-12-02 10:52:41,917] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 500 +28: [2022-12-02 10:52:41,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +25: [2022-12-02 10:52:41,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +25: [2022-12-02 10:52:41,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +28: [2022-12-02 10:52:41,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:41,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +48: [2022-12-02 10:52:41,930] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 391 +27: [2022-12-02 10:52:41,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +14: [2022-12-02 10:52:41,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +45: [2022-12-02 10:52:41,933] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 360 +48: [2022-12-02 10:52:41,934] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 390 + 2: [2022-12-02 10:52:41,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 2: [2022-12-02 10:52:41,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:41,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:41,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +48: [2022-12-02 10:52:41,943] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 388 +48: [2022-12-02 10:52:41,943] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 385 +45: [2022-12-02 10:52:41,946] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 363 +45: [2022-12-02 10:52:41,948] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 361 +62: [2022-12-02 10:52:41,948] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 502 + 2: [2022-12-02 10:52:41,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:41,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +48: [2022-12-02 10:52:41,950] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 384 + 2: [2022-12-02 10:52:41,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +45: [2022-12-02 10:52:41,954] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 362 +62: [2022-12-02 10:52:41,956] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 498 + 6: [2022-12-02 10:52:41,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +48: [2022-12-02 10:52:41,958] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 389 +11: [2022-12-02 10:52:41,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +48: [2022-12-02 10:52:41,961] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 387 +48: [2022-12-02 10:52:41,962] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 386 +24: [2022-12-02 10:52:41,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 6: [2022-12-02 10:52:41,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:41,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:41,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +45: [2022-12-02 10:52:41,973] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 366 +62: [2022-12-02 10:52:41,970] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 497 +62: [2022-12-02 10:52:41,972] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 501 +62: [2022-12-02 10:52:41,973] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 499 +20: [2022-12-02 10:52:41,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 6: [2022-12-02 10:52:41,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:41,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +45: [2022-12-02 10:52:41,977] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 365 +45: [2022-12-02 10:52:41,977] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 367 +46: [2022-12-02 10:52:41,978] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 369 +20: [2022-12-02 10:52:41,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +45: [2022-12-02 10:52:41,979] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 364 +19: [2022-12-02 10:52:41,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +62: [2022-12-02 10:52:41,979] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 503 +19: [2022-12-02 10:52:41,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:41,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:41,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:41,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +57: [2022-12-02 10:52:41,993] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 460 +26: [2022-12-02 10:52:41,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:41,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:41,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:41,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:41,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +46: [2022-12-02 10:52:41,994] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 375 +20: [2022-12-02 10:52:41,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:41,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +19: [2022-12-02 10:52:41,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:41,999] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:42,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:42,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:42,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 5: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +15: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +27: [2022-12-02 10:52:42,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-12-02 10:52:42,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +57: [2022-12-02 10:52:42,002] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 456 +26: [2022-12-02 10:52:42,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:42,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:42,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:42,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +26: [2022-12-02 10:52:42,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +57: [2022-12-02 10:52:42,006] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 458 +46: [2022-12-02 10:52:42,007] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 368 +57: [2022-12-02 10:52:42,008] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 459 +57: [2022-12-02 10:52:42,009] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 463 +57: [2022-12-02 10:52:42,010] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 457 +34: [2022-12-02 10:52:42,010] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 279 +57: [2022-12-02 10:52:42,011] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 462 +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-12-02 10:52:42,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +38: [2022-12-02 10:52:42,013] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 305 +34: [2022-12-02 10:52:42,013] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 275 +46: [2022-12-02 10:52:42,014] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 374 +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-12-02 10:52:42,017] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +57: [2022-12-02 10:52:42,018] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 461 +46: [2022-12-02 10:52:42,019] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 371 +46: [2022-12-02 10:52:42,019] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 370 +28: [2022-12-02 10:52:42,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:42,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:42,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:42,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:42,019] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +28: [2022-12-02 10:52:42,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +46: [2022-12-02 10:52:42,021] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 373 +27: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +46: [2022-12-02 10:52:42,026] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 372 +21: [2022-12-02 10:52:42,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +34: [2022-12-02 10:52:42,030] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 272 +27: [2022-12-02 10:52:42,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +34: [2022-12-02 10:52:42,030] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 278 +18: [2022-12-02 10:52:42,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +27: [2022-12-02 10:52:42,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:42,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:42,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:42,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:42,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:42,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +29: [2022-12-02 10:52:42,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +21: [2022-12-02 10:52:42,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +38: [2022-12-02 10:52:42,039] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 306 +34: [2022-12-02 10:52:42,040] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 273 +11: [2022-12-02 10:52:42,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:42,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +56: [2022-12-02 10:52:42,041] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 452 +18: [2022-12-02 10:52:42,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +38: [2022-12-02 10:52:42,043] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 310 +18: [2022-12-02 10:52:42,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:42,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +34: [2022-12-02 10:52:42,045] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 274 +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +60: [2022-12-02 10:52:42,047] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 485 +18: [2022-12-02 10:52:42,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:42,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:42,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +18: [2022-12-02 10:52:42,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +34: [2022-12-02 10:52:42,048] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 277 +22: [2022-12-02 10:52:42,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +22: [2022-12-02 10:52:42,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +38: [2022-12-02 10:52:42,052] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 304 +56: [2022-12-02 10:52:42,052] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 455 +31: [2022-12-02 10:52:42,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:42,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:42,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:42,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +11: [2022-12-02 10:52:42,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:42,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:42,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:42,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +52: [2022-12-02 10:52:42,054] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 416 +31: [2022-12-02 10:52:42,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:42,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +31: [2022-12-02 10:52:42,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +34: [2022-12-02 10:52:42,054] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 276 +38: [2022-12-02 10:52:42,055] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 307 +38: [2022-12-02 10:52:42,055] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 311 +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-12-02 10:52:42,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +59: [2022-12-02 10:52:42,056] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 472 +52: [2022-12-02 10:52:42,061] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 417 +47: [2022-12-02 10:52:42,061] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 380 +60: [2022-12-02 10:52:42,061] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 480 +19: [2022-12-02 10:52:42,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +11: [2022-12-02 10:52:42,062] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-12-02 10:52:42,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,065] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +56: [2022-12-02 10:52:42,065] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 450 +56: [2022-12-02 10:52:42,065] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 454 +52: [2022-12-02 10:52:42,067] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 419 + 5: [2022-12-02 10:52:42,067] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +52: [2022-12-02 10:52:42,067] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 418 +19: [2022-12-02 10:52:42,068] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +38: [2022-12-02 10:52:42,069] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 309 +26: [2022-12-02 10:52:42,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:42,069] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +56: [2022-12-02 10:52:42,069] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 449 +56: [2022-12-02 10:52:42,070] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 451 +56: [2022-12-02 10:52:42,070] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 453 +56: [2022-12-02 10:52:42,071] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 448 +26: [2022-12-02 10:52:42,071] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +59: [2022-12-02 10:52:42,072] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 478 +38: [2022-12-02 10:52:42,075] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 308 +59: [2022-12-02 10:52:42,076] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 479 +52: [2022-12-02 10:52:42,079] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 420 + 5: [2022-12-02 10:52:42,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 5: [2022-12-02 10:52:42,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +47: [2022-12-02 10:52:42,081] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 381 + 5: [2022-12-02 10:52:42,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:42,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:42,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:42,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +47: [2022-12-02 10:52:42,083] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 377 + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +47: [2022-12-02 10:52:42,083] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 376 +19: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +19: [2022-12-02 10:52:42,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +47: [2022-12-02 10:52:42,086] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 382 +47: [2022-12-02 10:52:42,087] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 383 +26: [2022-12-02 10:52:42,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 3: [2022-12-02 10:52:42,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,089] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 30 +47: [2022-12-02 10:52:42,090] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 378 +26: [2022-12-02 10:52:42,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:42,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:42,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +26: [2022-12-02 10:52:42,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:42,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +47: [2022-12-02 10:52:42,094] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 379 +17: [2022-12-02 10:52:42,095] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 139 + 4: [2022-12-02 10:52:42,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +52: [2022-12-02 10:52:42,095] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 422 +52: [2022-12-02 10:52:42,095] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 423 + 4: [2022-12-02 10:52:42,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:42,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:42,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:42,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:42,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:42,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... + 4: [2022-12-02 10:52:42,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt... +52: [2022-12-02 10:52:42,097] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 421 +59: [2022-12-02 10:52:42,099] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 474 +60: [2022-12-02 10:52:42,101] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 487 +59: [2022-12-02 10:52:42,101] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 473 + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-12-02 10:52:42,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +60: [2022-12-02 10:52:42,103] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 483 +60: [2022-12-02 10:52:42,107] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 486 +60: [2022-12-02 10:52:42,110] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 481 +21: [2022-12-02 10:52:42,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,110] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-12-02 10:52:42,111] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +59: [2022-12-02 10:52:42,111] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 477 +29: [2022-12-02 10:52:42,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,112] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,113] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +60: [2022-12-02 10:52:42,117] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 484 +43: [2022-12-02 10:52:42,117] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 345 +18: [2022-12-02 10:52:42,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,118] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +29: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-12-02 10:52:42,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +60: [2022-12-02 10:52:42,120] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 482 +59: [2022-12-02 10:52:42,121] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 475 +59: [2022-12-02 10:52:42,121] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 476 +21: [2022-12-02 10:52:42,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +21: [2022-12-02 10:52:42,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +43: [2022-12-02 10:52:42,126] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 350 + 0: [2022-12-02 10:52:42,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-02 10:52:42,129] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 1 +51: [2022-12-02 10:52:42,129] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 415 +22: [2022-12-02 10:52:42,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +22: [2022-12-02 10:52:42,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,130] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-12-02 10:52:42,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +58: [2022-12-02 10:52:42,133] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 471 +31: [2022-12-02 10:52:42,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +31: [2022-12-02 10:52:42,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +43: [2022-12-02 10:52:42,135] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 351 +18: [2022-12-02 10:52:42,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +18: [2022-12-02 10:52:42,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +17: [2022-12-02 10:52:42,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,137] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 138 + 0: [2022-12-02 10:52:42,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +43: [2022-12-02 10:52:42,138] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 344 + 0: [2022-12-02 10:52:42,138] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 6 +37: [2022-12-02 10:52:42,139] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 302 +58: [2022-12-02 10:52:42,144] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 464 +43: [2022-12-02 10:52:42,144] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 349 + 3: [2022-12-02 10:52:42,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,147] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 29 +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-12-02 10:52:42,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-12-02 10:52:42,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +17: [2022-12-02 10:52:42,150] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 139 +43: [2022-12-02 10:52:42,150] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 348 +43: [2022-12-02 10:52:42,151] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 347 +43: [2022-12-02 10:52:42,155] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 346 +37: [2022-12-02 10:52:42,156] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 303 +51: [2022-12-02 10:52:42,160] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 413 +58: [2022-12-02 10:52:42,162] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 470 +12: [2022-12-02 10:52:42,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,164] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 99 +51: [2022-12-02 10:52:42,164] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 414 +51: [2022-12-02 10:52:42,166] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 411 +58: [2022-12-02 10:52:42,169] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 465 +51: [2022-12-02 10:52:42,169] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 410 +51: [2022-12-02 10:52:42,170] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 412 +51: [2022-12-02 10:52:42,170] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 408 + 4: [2022-12-02 10:52:42,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +37: [2022-12-02 10:52:42,171] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 299 +58: [2022-12-02 10:52:42,171] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 467 + 4: [2022-12-02 10:52:42,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 0: [2022-12-02 10:52:42,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-02 10:52:42,172] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 7 +37: [2022-12-02 10:52:42,174] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 301 +51: [2022-12-02 10:52:42,175] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 409 + 4: [2022-12-02 10:52:42,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. + 4: [2022-12-02 10:52:42,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/layer_20-model_00-model_states.pt. +37: [2022-12-02 10:52:42,177] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 298 +17: [2022-12-02 10:52:42,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,178] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 141 +37: [2022-12-02 10:52:42,178] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 296 +58: [2022-12-02 10:52:42,178] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 466 +37: [2022-12-02 10:52:42,180] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 297 +37: [2022-12-02 10:52:42,180] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 300 +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-12-02 10:52:42,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 3: [2022-12-02 10:52:42,182] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 30 +58: [2022-12-02 10:52:42,182] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 469 +50: [2022-12-02 10:52:42,186] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 406 +61: [2022-12-02 10:52:42,186] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 489 +58: [2022-12-02 10:52:42,187] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 468 +50: [2022-12-02 10:52:42,190] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 405 +53: [2022-12-02 10:52:42,190] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 425 +61: [2022-12-02 10:52:42,192] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 494 +12: [2022-12-02 10:52:42,195] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 99 +54: [2022-12-02 10:52:42,196] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 434 +17: [2022-12-02 10:52:42,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,197] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 137 + 7: [2022-12-02 10:52:42,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,199] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 61 + 1: [2022-12-02 10:52:42,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +53: [2022-12-02 10:52:42,199] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 431 + 1: [2022-12-02 10:52:42,200] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 15 +61: [2022-12-02 10:52:42,200] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 491 +53: [2022-12-02 10:52:42,201] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 428 + 3: [2022-12-02 10:52:42,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +61: [2022-12-02 10:52:42,202] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 495 + 3: [2022-12-02 10:52:42,202] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 27 +61: [2022-12-02 10:52:42,202] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 488 + 1: [2022-12-02 10:52:42,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +50: [2022-12-02 10:52:42,203] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 402 +53: [2022-12-02 10:52:42,204] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 426 + 1: [2022-12-02 10:52:42,204] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 9 +54: [2022-12-02 10:52:42,204] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 438 +63: [2022-12-02 10:52:42,205] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 505 +61: [2022-12-02 10:52:42,207] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 490 +54: [2022-12-02 10:52:42,208] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 432 + 0: [2022-12-02 10:52:42,208] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 6 +53: [2022-12-02 10:52:42,209] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 424 +10: [2022-12-02 10:52:42,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,209] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 83 +50: [2022-12-02 10:52:42,211] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 403 + 0: [2022-12-02 10:52:42,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +63: [2022-12-02 10:52:42,211] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 509 + 0: [2022-12-02 10:52:42,212] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 4 + 9: [2022-12-02 10:52:42,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +53: [2022-12-02 10:52:42,212] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 429 + 9: [2022-12-02 10:52:42,213] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 75 +50: [2022-12-02 10:52:42,214] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 407 +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-12-02 10:52:42,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 3: [2022-12-02 10:52:42,216] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 29 +61: [2022-12-02 10:52:42,216] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 493 +61: [2022-12-02 10:52:42,216] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 492 +63: [2022-12-02 10:52:42,216] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 504 +63: [2022-12-02 10:52:42,217] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 510 +50: [2022-12-02 10:52:42,218] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 404 +17: [2022-12-02 10:52:42,216] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 138 +63: [2022-12-02 10:52:42,218] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 506 + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-12-02 10:52:42,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +54: [2022-12-02 10:52:42,220] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 433 +54: [2022-12-02 10:52:42,220] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 437 +54: [2022-12-02 10:52:42,220] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 439 +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-12-02 10:52:42,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:42,221] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 187 +63: [2022-12-02 10:52:42,222] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 508 +54: [2022-12-02 10:52:42,224] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 435 +63: [2022-12-02 10:52:42,224] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 511 +63: [2022-12-02 10:52:42,225] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 507 +17: [2022-12-02 10:52:42,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +50: [2022-12-02 10:52:42,227] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 401 +17: [2022-12-02 10:52:42,223] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 143 +50: [2022-12-02 10:52:42,227] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 400 +53: [2022-12-02 10:52:42,228] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 427 +54: [2022-12-02 10:52:42,229] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 436 +53: [2022-12-02 10:52:42,229] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 430 +10: [2022-12-02 10:52:42,229] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,230] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 86 +12: [2022-12-02 10:52:42,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,230] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 96 + 1: [2022-12-02 10:52:42,231] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 15 +23: [2022-12-02 10:52:42,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-02 10:52:42,234] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 186 + 0: [2022-12-02 10:52:42,236] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 7 + 1: [2022-12-02 10:52:42,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-02 10:52:42,237] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 8 + 8: [2022-12-02 10:52:42,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,244] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 64 + 7: [2022-12-02 10:52:42,244] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 61 +17: [2022-12-02 10:52:42,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,246] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 83 +17: [2022-12-02 10:52:42,246] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 136 +36: [2022-12-02 10:52:42,246] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 289 +12: [2022-12-02 10:52:42,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,247] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 97 +17: [2022-12-02 10:52:42,253] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 141 + 1: [2022-12-02 10:52:42,253] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 9 +23: [2022-12-02 10:52:42,253] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 187 + 0: [2022-12-02 10:52:42,258] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 1 + 3: [2022-12-02 10:52:42,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,259] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 28 + 1: [2022-12-02 10:52:42,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 1: [2022-12-02 10:52:42,261] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 12 + 8: [2022-12-02 10:52:42,261] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 68 + 7: [2022-12-02 10:52:42,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,262] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 56 +36: [2022-12-02 10:52:42,265] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 288 +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-12-02 10:52:42,266] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +36: [2022-12-02 10:52:42,266] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 295 +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-12-02 10:52:42,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... + 1: [2022-12-02 10:52:42,269] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +36: [2022-12-02 10:52:42,269] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 294 + 1: [2022-12-02 10:52:42,269] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 13 + 1: [2022-12-02 10:52:42,270] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 10 +17: [2022-12-02 10:52:42,271] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,271] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 140 +36: [2022-12-02 10:52:42,272] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 290 +17: [2022-12-02 10:52:42,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,273] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 142 +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-12-02 10:52:42,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-12-02 10:52:42,274] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +36: [2022-12-02 10:52:42,274] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 292 + 3: [2022-12-02 10:52:42,275] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 27 +23: [2022-12-02 10:52:42,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +23: [2022-12-02 10:52:42,277] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 188 +36: [2022-12-02 10:52:42,277] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 291 +10: [2022-12-02 10:52:42,277] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 82 +23: [2022-12-02 10:52:42,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. + 0: [2022-12-02 10:52:42,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +23: [2022-12-02 10:52:42,277] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 184 +36: [2022-12-02 10:52:42,277] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 293 + 0: [2022-12-02 10:52:42,278] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 3 +23: [2022-12-02 10:52:42,278] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-02 10:52:42,278] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 189 + 7: [2022-12-02 10:52:42,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,281] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 75 + 7: [2022-12-02 10:52:42,281] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 59 + 1: [2022-12-02 10:52:42,282] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 8 +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +23: [2022-12-02 10:52:42,284] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 186 +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-12-02 10:52:42,284] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 0: [2022-12-02 10:52:42,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-02 10:52:42,286] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 5 +12: [2022-12-02 10:52:42,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,287] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 86 +12: [2022-12-02 10:52:42,287] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 103 +12: [2022-12-02 10:52:42,288] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 96 + 9: [2022-12-02 10:52:42,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,298] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 73 + 8: [2022-12-02 10:52:42,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,305] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 67 +12: [2022-12-02 10:52:42,305] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,306] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 100 + 8: [2022-12-02 10:52:42,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,312] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 69 + 9: [2022-12-02 10:52:42,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,313] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 72 + 9: [2022-12-02 10:52:42,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,318] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 74 + 8: [2022-12-02 10:52:42,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,318] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 102 + 8: [2022-12-02 10:52:42,320] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 70 + 7: [2022-12-02 10:52:42,321] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 56 +12: [2022-12-02 10:52:42,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 0: [2022-12-02 10:52:42,322] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,322] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 98 + 0: [2022-12-02 10:52:42,323] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 0 + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-12-02 10:52:42,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 7: [2022-12-02 10:52:42,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,325] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,326] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 62 + 3: [2022-12-02 10:52:42,326] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 25 +10: [2022-12-02 10:52:42,327] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,328] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 84 +23: [2022-12-02 10:52:42,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,332] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 64 +23: [2022-12-02 10:52:42,332] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 185 +10: [2022-12-02 10:52:42,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,336] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 143 +10: [2022-12-02 10:52:42,337] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 85 +17: [2022-12-02 10:52:42,337] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 137 + 7: [2022-12-02 10:52:42,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 1: [2022-12-02 10:52:42,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 57 + 1: [2022-12-02 10:52:42,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 11 + 7: [2022-12-02 10:52:42,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,339] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 60 +12: [2022-12-02 10:52:42,342] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 97 + 0: [2022-12-02 10:52:42,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-12-02 10:52:42,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 2 + 1: [2022-12-02 10:52:42,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,346] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 109 + 1: [2022-12-02 10:52:42,346] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 14 + 8: [2022-12-02 10:52:42,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 66 +23: [2022-12-02 10:52:42,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-02 10:52:42,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 191 +10: [2022-12-02 10:52:42,352] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 82 +23: [2022-12-02 10:52:42,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-02 10:52:42,353] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 190 + 3: [2022-12-02 10:52:42,355] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 28 +16: [2022-12-02 10:52:42,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 133 + 9: [2022-12-02 10:52:42,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,364] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 76 + 8: [2022-12-02 10:52:42,366] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 68 + 8: [2022-12-02 10:52:42,366] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 67 + 3: [2022-12-02 10:52:42,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,368] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 26 + 9: [2022-12-02 10:52:42,369] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 72 + 9: [2022-12-02 10:52:42,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,370] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 79 + 8: [2022-12-02 10:52:42,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,371] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 65 +16: [2022-12-02 10:52:42,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,375] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 128 +10: [2022-12-02 10:52:42,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,375] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 71 + 9: [2022-12-02 10:52:42,375] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 74 +10: [2022-12-02 10:52:42,375] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 80 + 3: [2022-12-02 10:52:42,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,376] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 24 + 7: [2022-12-02 10:52:42,377] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 59 + 0: [2022-12-02 10:52:42,380] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 3 +12: [2022-12-02 10:52:42,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-02 10:52:42,382] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 101 + 3: [2022-12-02 10:52:42,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-02 10:52:42,383] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 31 + 9: [2022-12-02 10:52:42,397] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-02 10:52:42,397] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 77 +16: [2022-12-02 10:52:42,398] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 133 +10: [2022-12-02 10:52:42,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,404] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 87 + 0: [2022-12-02 10:52:42,405] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 4 +30: [2022-12-02 10:52:42,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,407] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 243 +14: [2022-12-02 10:52:42,407] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,407] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 71 +14: [2022-12-02 10:52:42,407] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 119 + 1: [2022-12-02 10:52:42,409] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 11 +12: [2022-12-02 10:52:42,414] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 103 +23: [2022-12-02 10:52:42,416] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 191 + 7: [2022-12-02 10:52:42,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 1: [2022-12-02 10:52:42,417] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 14 + 7: [2022-12-02 10:52:42,418] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 63 +10: [2022-12-02 10:52:42,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,419] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 81 +30: [2022-12-02 10:52:42,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,421] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 246 +12: [2022-12-02 10:52:42,425] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 100 +13: [2022-12-02 10:52:42,425] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,426] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 106 +16: [2022-12-02 10:52:42,429] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,429] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 130 +13: [2022-12-02 10:52:42,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,432] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 107 + 1: [2022-12-02 10:52:42,434] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 13 + 2: [2022-12-02 10:52:42,435] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 8: [2022-12-02 10:52:42,435] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 65 + 2: [2022-12-02 10:52:42,436] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 22 + 7: [2022-12-02 10:52:42,436] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,436] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 58 +23: [2022-12-02 10:52:42,436] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 190 + 3: [2022-12-02 10:52:42,441] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 31 +25: [2022-12-02 10:52:42,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,443] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 201 +12: [2022-12-02 10:52:42,445] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 101 +25: [2022-12-02 10:52:42,446] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,446] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 206 +13: [2022-12-02 10:52:42,446] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 109 +16: [2022-12-02 10:52:42,447] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,447] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 131 +23: [2022-12-02 10:52:42,447] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 188 + 8: [2022-12-02 10:52:42,449] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 70 +23: [2022-12-02 10:52:42,452] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 184 +30: [2022-12-02 10:52:42,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,454] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,455] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 245 +14: [2022-12-02 10:52:42,455] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 116 +16: [2022-12-02 10:52:42,456] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,457] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 135 + 9: [2022-12-02 10:52:42,457] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,457] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 119 + 9: [2022-12-02 10:52:42,458] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 78 +10: [2022-12-02 10:52:42,458] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 87 +30: [2022-12-02 10:52:42,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,460] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 240 +24: [2022-12-02 10:52:42,460] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 195 +13: [2022-12-02 10:52:42,460] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 80 +13: [2022-12-02 10:52:42,461] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 108 + 9: [2022-12-02 10:52:42,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 73 + 1: [2022-12-02 10:52:42,462] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 10 + 9: [2022-12-02 10:52:42,462] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 77 + 8: [2022-12-02 10:52:42,463] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 66 + 6: [2022-12-02 10:52:42,463] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +17: [2022-12-02 10:52:42,464] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 142 + 6: [2022-12-02 10:52:42,464] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 55 +16: [2022-12-02 10:52:42,469] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 128 +27: [2022-12-02 10:52:42,474] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,475] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 220 +20: [2022-12-02 10:52:42,475] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,475] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 160 +13: [2022-12-02 10:52:42,480] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,480] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 104 + 8: [2022-12-02 10:52:42,483] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 69 + 0: [2022-12-02 10:52:42,485] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 5 + 0: [2022-12-02 10:52:42,485] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 0 + 0: checkpoint version 3.0 +30: [2022-12-02 10:52:42,486] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,486] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 241 + 3: [2022-12-02 10:52:42,487] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 25 +17: [2022-12-02 10:52:42,487] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 140 +30: [2022-12-02 10:52:42,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,487] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 242 +20: [2022-12-02 10:52:42,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,489] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 162 +25: [2022-12-02 10:52:42,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,490] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 207 + 2: [2022-12-02 10:52:42,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-02 10:52:42,491] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 21 +25: [2022-12-02 10:52:42,493] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,494] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 204 +23: [2022-12-02 10:52:42,495] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 189 +24: [2022-12-02 10:52:42,495] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,496] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 199 +25: [2022-12-02 10:52:42,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,497] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 205 +25: [2022-12-02 10:52:42,497] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,498] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 202 +13: [2022-12-02 10:52:42,498] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,499] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,499] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 105 +14: [2022-12-02 10:52:42,499] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 113 +16: [2022-12-02 10:52:42,502] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,502] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 129 + 2: [2022-12-02 10:52:42,502] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 22 +17: [2022-12-02 10:52:42,505] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 136 + 3: [2022-12-02 10:52:42,506] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 24 + 1: [2022-12-02 10:52:42,509] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 12 +24: [2022-12-02 10:52:42,510] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 195 + 6: [2022-12-02 10:52:42,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-02 10:52:42,512] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 52 +20: [2022-12-02 10:52:42,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 6: [2022-12-02 10:52:42,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,514] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 165 + 6: [2022-12-02 10:52:42,514] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 51 +16: [2022-12-02 10:52:42,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,515] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 134 +14: [2022-12-02 10:52:42,517] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 116 +15: [2022-12-02 10:52:42,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,517] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 106 +15: [2022-12-02 10:52:42,517] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 123 +15: [2022-12-02 10:52:42,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,520] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 124 +16: [2022-12-02 10:52:42,520] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 132 +25: [2022-12-02 10:52:42,520] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 206 +28: [2022-12-02 10:52:42,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,521] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 227 + 2: [2022-12-02 10:52:42,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,523] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,524] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 244 + 2: [2022-12-02 10:52:42,524] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 23 +25: [2022-12-02 10:52:42,524] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 201 +12: [2022-12-02 10:52:42,524] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 98 +13: [2022-12-02 10:52:42,525] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,525] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 111 +27: [2022-12-02 10:52:42,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,531] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 223 +27: [2022-12-02 10:52:42,532] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 220 + 6: [2022-12-02 10:52:42,532] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 55 +24: [2022-12-02 10:52:42,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,533] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 194 +13: [2022-12-02 10:52:42,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,535] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 110 +30: [2022-12-02 10:52:42,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,539] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 247 + 6: [2022-12-02 10:52:42,540] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-02 10:52:42,540] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 53 + 2: [2022-12-02 10:52:42,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,541] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 84 +14: [2022-12-02 10:52:42,541] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 114 + 2: [2022-12-02 10:52:42,541] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 18 +21: [2022-12-02 10:52:42,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,542] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 169 + 6: [2022-12-02 10:52:42,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-02 10:52:42,546] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 54 +25: [2022-12-02 10:52:42,546] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,547] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 203 + 7: [2022-12-02 10:52:42,547] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 58 +20: [2022-12-02 10:52:42,548] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,548] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 161 +12: [2022-12-02 10:52:42,549] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 102 +20: [2022-12-02 10:52:42,549] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,549] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 160 +20: [2022-12-02 10:52:42,549] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 167 +25: [2022-12-02 10:52:42,551] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-02 10:52:42,551] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 200 +13: [2022-12-02 10:52:42,551] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 107 + 2: [2022-12-02 10:52:42,553] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 21 +30: [2022-12-02 10:52:42,557] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 243 + 6: [2022-12-02 10:52:42,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-02 10:52:42,559] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 49 +18: [2022-12-02 10:52:42,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,562] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 145 +24: [2022-12-02 10:52:42,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,563] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 198 +15: [2022-12-02 10:52:42,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,564] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 120 +28: [2022-12-02 10:52:42,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,565] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 228 + 2: [2022-12-02 10:52:42,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-02 10:52:42,568] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 20 +28: [2022-12-02 10:52:42,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,570] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 229 +14: [2022-12-02 10:52:42,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,571] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 115 +14: [2022-12-02 10:52:42,571] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 117 +20: [2022-12-02 10:52:42,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,571] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 166 +24: [2022-12-02 10:52:42,571] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 196 +10: [2022-12-02 10:52:42,572] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 85 + 2: [2022-12-02 10:52:42,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-02 10:52:42,573] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 17 +11: [2022-12-02 10:52:42,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 7: [2022-12-02 10:52:42,573] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 60 +11: [2022-12-02 10:52:42,574] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 89 + 6: [2022-12-02 10:52:42,574] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-02 10:52:42,574] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 48 +16: [2022-12-02 10:52:42,577] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 134 +21: [2022-12-02 10:52:42,579] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 169 +20: [2022-12-02 10:52:42,579] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 162 +20: [2022-12-02 10:52:42,579] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 165 + 2: [2022-12-02 10:52:42,580] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +30: [2022-12-02 10:52:42,580] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 242 + 2: [2022-12-02 10:52:42,580] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 19 + 7: [2022-12-02 10:52:42,581] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 57 +16: [2022-12-02 10:52:42,581] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 130 +16: [2022-12-02 10:52:42,583] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 131 + 6: [2022-12-02 10:52:42,583] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +16: [2022-12-02 10:52:42,583] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 132 + 6: [2022-12-02 10:52:42,584] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 50 +24: [2022-12-02 10:52:42,584] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,584] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 193 +14: [2022-12-02 10:52:42,585] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,585] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 112 +16: [2022-12-02 10:52:42,586] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 129 +27: [2022-12-02 10:52:42,586] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,587] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 217 + 9: [2022-12-02 10:52:42,587] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 79 +27: [2022-12-02 10:52:42,589] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 223 +27: [2022-12-02 10:52:42,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,590] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 221 +20: [2022-12-02 10:52:42,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. + 5: [2022-12-02 10:52:42,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,592] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 163 +27: [2022-12-02 10:52:42,592] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 216 + 5: [2022-12-02 10:52:42,592] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 43 +31: [2022-12-02 10:52:42,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,594] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 251 + 3: [2022-12-02 10:52:42,595] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 26 +18: [2022-12-02 10:52:42,596] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 145 +15: [2022-12-02 10:52:42,596] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,597] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 122 +11: [2022-12-02 10:52:42,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-02 10:52:42,597] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 92 + 2: [2022-12-02 10:52:42,597] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-12-02 10:52:42,598] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 16 + 2: [2022-12-02 10:52:42,599] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 23 +27: [2022-12-02 10:52:42,599] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,600] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 219 +23: [2022-12-02 10:52:42,601] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 185 + 7: [2022-12-02 10:52:42,601] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 62 +11: [2022-12-02 10:52:42,601] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-02 10:52:42,602] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 90 +19: [2022-12-02 10:52:42,602] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-02 10:52:42,602] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 152 +31: [2022-12-02 10:52:42,603] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,603] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 253 +13: [2022-12-02 10:52:42,606] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 110 +26: [2022-12-02 10:52:42,606] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,606] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 210 +15: [2022-12-02 10:52:42,607] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 124 +28: [2022-12-02 10:52:42,608] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,608] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 224 +24: [2022-12-02 10:52:42,609] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,609] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 192 +22: [2022-12-02 10:52:42,610] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,610] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 176 + 5: [2022-12-02 10:52:42,611] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-02 10:52:42,612] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 45 +15: [2022-12-02 10:52:42,612] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,613] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 127 +28: [2022-12-02 10:52:42,613] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 231 +29: [2022-12-02 10:52:42,613] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,613] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 234 +20: [2022-12-02 10:52:42,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-12-02 10:52:42,614] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 164 +15: [2022-12-02 10:52:42,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,616] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 125 +15: [2022-12-02 10:52:42,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,618] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 121 +27: [2022-12-02 10:52:42,618] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,618] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 218 +28: [2022-12-02 10:52:42,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,619] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 225 +19: [2022-12-02 10:52:42,619] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-02 10:52:42,620] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 156 + 5: [2022-12-02 10:52:42,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-02 10:52:42,621] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 41 + 0: [2022-12-02 10:52:42,627] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 2 +30: [2022-12-02 10:52:42,628] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 240 +19: [2022-12-02 10:52:42,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-12-02 10:52:42,630] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 158 +19: [2022-12-02 10:52:42,631] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 152 + 7: [2022-12-02 10:52:42,632] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 63 +26: [2022-12-02 10:52:42,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,633] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 212 +11: [2022-12-02 10:52:42,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +11: [2022-12-02 10:52:42,635] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 91 +18: [2022-12-02 10:52:42,636] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 147 +28: [2022-12-02 10:52:42,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,637] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 230 +21: [2022-12-02 10:52:42,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,637] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 168 +18: [2022-12-02 10:52:42,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,643] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 146 + 5: [2022-12-02 10:52:42,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +10: [2022-12-02 10:52:42,643] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 81 +19: [2022-12-02 10:52:42,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +11: [2022-12-02 10:52:42,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +19: [2022-12-02 10:52:42,644] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 159 +11: [2022-12-02 10:52:42,644] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 94 +11: [2022-12-02 10:52:42,645] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 92 +21: [2022-12-02 10:52:42,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 5: [2022-12-02 10:52:42,643] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 47 +11: [2022-12-02 10:52:42,645] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 89 +11: [2022-12-02 10:52:42,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,645] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 172 +31: [2022-12-02 10:52:42,645] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 251 +11: [2022-12-02 10:52:42,646] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 93 +11: [2022-12-02 10:52:42,646] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-02 10:52:42,646] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 88 +26: [2022-12-02 10:52:42,647] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 210 +29: [2022-12-02 10:52:42,647] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 234 + 9: [2022-12-02 10:52:42,649] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 78 +24: [2022-12-02 10:52:42,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-02 10:52:42,654] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 197 +15: [2022-12-02 10:52:42,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-02 10:52:42,655] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 126 + 5: [2022-12-02 10:52:42,655] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 45 +22: [2022-12-02 10:52:42,656] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 176 +28: [2022-12-02 10:52:42,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,657] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 226 + 5: [2022-12-02 10:52:42,658] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 43 + 5: [2022-12-02 10:52:42,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-02 10:52:42,659] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 42 +18: [2022-12-02 10:52:42,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,660] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 151 +27: [2022-12-02 10:52:42,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,660] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 222 +31: [2022-12-02 10:52:42,661] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 253 +14: [2022-12-02 10:52:42,663] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 115 +29: [2022-12-02 10:52:42,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,663] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 237 +19: [2022-12-02 10:52:42,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,665] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 117 +19: [2022-12-02 10:52:42,665] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 154 +21: [2022-12-02 10:52:42,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,666] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 175 +19: [2022-12-02 10:52:42,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +28: [2022-12-02 10:52:42,589] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 227 +19: [2022-12-02 10:52:42,667] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 157 +14: [2022-12-02 10:52:42,671] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 112 + 9: [2022-12-02 10:52:42,677] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 76 +19: [2022-12-02 10:52:42,677] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 156 +14: [2022-12-02 10:52:42,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +13: [2022-12-02 10:52:42,678] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 108 +22: [2022-12-02 10:52:42,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +14: [2022-12-02 10:52:42,678] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 118 +22: [2022-12-02 10:52:42,678] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 178 + 4: [2022-12-02 10:52:42,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,679] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 36 + 5: [2022-12-02 10:52:42,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 41 +16: [2022-12-02 10:52:42,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 135 +26: [2022-12-02 10:52:42,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. + 2: [2022-12-02 10:52:42,683] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 16 +26: [2022-12-02 10:52:42,683] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 211 +22: [2022-12-02 10:52:42,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +19: [2022-12-02 10:52:42,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,684] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 183 +19: [2022-12-02 10:52:42,684] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 155 +28: [2022-12-02 10:52:42,684] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 229 + 2: [2022-12-02 10:52:42,685] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 17 + 2: [2022-12-02 10:52:42,686] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 19 +29: [2022-12-02 10:52:42,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,688] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 236 +26: [2022-12-02 10:52:42,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,690] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 213 +11: [2022-12-02 10:52:42,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-02 10:52:42,691] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 95 +21: [2022-12-02 10:52:42,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,692] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 170 +24: [2022-12-02 10:52:42,695] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 196 +31: [2022-12-02 10:52:42,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,696] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 255 +18: [2022-12-02 10:52:42,696] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 147 +31: [2022-12-02 10:52:42,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,696] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 254 +19: [2022-12-02 10:52:42,696] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 158 +18: [2022-12-02 10:52:42,697] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 144 +24: [2022-12-02 10:52:42,697] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 199 +25: [2022-12-02 10:52:42,698] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 202 +18: [2022-12-02 10:52:42,699] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 146 +24: [2022-12-02 10:52:42,701] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 194 +26: [2022-12-02 10:52:42,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,702] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 215 + 5: [2022-12-02 10:52:42,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,704] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 149 + 5: [2022-12-02 10:52:42,704] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 40 +18: [2022-12-02 10:52:42,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,706] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 148 + 4: [2022-12-02 10:52:42,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,707] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 34 +28: [2022-12-02 10:52:42,709] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 225 +24: [2022-12-02 10:52:42,710] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 198 +26: [2022-12-02 10:52:42,711] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 212 +27: [2022-12-02 10:52:42,712] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 217 +27: [2022-12-02 10:52:42,712] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 216 + 4: [2022-12-02 10:52:42,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +27: [2022-12-02 10:52:42,716] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 218 +29: [2022-12-02 10:52:42,716] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 239 + 4: [2022-12-02 10:52:42,716] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 35 +15: [2022-12-02 10:52:42,716] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 123 +31: [2022-12-02 10:52:42,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,716] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 252 +31: [2022-12-02 10:52:42,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,717] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 250 +30: [2022-12-02 10:52:42,718] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 245 +30: [2022-12-02 10:52:42,718] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 244 +19: [2022-12-02 10:52:42,719] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 155 +26: [2022-12-02 10:52:42,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,721] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 214 +19: [2022-12-02 10:52:42,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-02 10:52:42,721] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 153 +18: [2022-12-02 10:52:42,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-02 10:52:42,723] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 150 +29: [2022-12-02 10:52:42,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,724] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 238 +20: [2022-12-02 10:52:42,725] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 163 +26: [2022-12-02 10:52:42,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-02 10:52:42,727] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 209 +22: [2022-12-02 10:52:42,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,728] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 182 + 4: [2022-12-02 10:52:42,730] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 36 +21: [2022-12-02 10:52:42,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,732] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 171 +28: [2022-12-02 10:52:42,732] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 224 + 4: [2022-12-02 10:52:42,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,735] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 37 +13: [2022-12-02 10:52:42,735] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 105 +29: [2022-12-02 10:52:42,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,736] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 232 + 5: [2022-12-02 10:52:42,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-12-02 10:52:42,738] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 44 +22: [2022-12-02 10:52:42,739] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 183 +31: [2022-12-02 10:52:42,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,739] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 248 + 6: [2022-12-02 10:52:42,739] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 49 +22: [2022-12-02 10:52:42,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,740] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 180 +22: [2022-12-02 10:52:42,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,747] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 177 +22: [2022-12-02 10:52:42,747] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 181 +21: [2022-12-02 10:52:42,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,748] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 174 +21: [2022-12-02 10:52:42,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,749] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 173 +11: [2022-12-02 10:52:42,749] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 95 + 6: [2022-12-02 10:52:42,753] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 52 +26: [2022-12-02 10:52:42,756] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 211 +31: [2022-12-02 10:52:42,757] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 254 +30: [2022-12-02 10:52:42,758] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 246 + 4: [2022-12-02 10:52:42,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,759] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 39 + 6: [2022-12-02 10:52:42,759] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 53 +21: [2022-12-02 10:52:42,764] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 175 +20: [2022-12-02 10:52:42,764] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 166 +27: [2022-12-02 10:52:42,766] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 219 +15: [2022-12-02 10:52:42,770] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 125 +29: [2022-12-02 10:52:42,772] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 239 + 6: [2022-12-02 10:52:42,772] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 51 +28: [2022-12-02 10:52:42,774] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 230 +28: [2022-12-02 10:52:42,774] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 228 +26: [2022-12-02 10:52:42,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +21: [2022-12-02 10:52:42,775] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 170 +26: [2022-12-02 10:52:42,775] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 208 +28: [2022-12-02 10:52:42,776] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 231 +29: [2022-12-02 10:52:42,777] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 237 +11: [2022-12-02 10:52:42,779] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 90 +18: [2022-12-02 10:52:42,783] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 150 +26: [2022-12-02 10:52:42,784] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 214 + 2: [2022-12-02 10:52:42,785] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 18 + 4: [2022-12-02 10:52:42,790] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 34 +31: [2022-12-02 10:52:42,791] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 248 +14: [2022-12-02 10:52:42,791] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 118 +29: [2022-12-02 10:52:42,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,791] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 235 +25: [2022-12-02 10:52:42,792] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 207 + 6: [2022-12-02 10:52:42,795] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 54 + 4: [2022-12-02 10:52:42,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,797] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 33 +31: [2022-12-02 10:52:42,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-02 10:52:42,800] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 249 +20: [2022-12-02 10:52:42,801] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 164 +20: [2022-12-02 10:52:42,805] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 161 +24: [2022-12-02 10:52:42,809] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 193 +27: [2022-12-02 10:52:42,811] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 222 +19: [2022-12-02 10:52:42,820] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 153 + 4: [2022-12-02 10:52:42,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 32 +31: [2022-12-02 10:52:42,829] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 255 +24: [2022-12-02 10:52:42,830] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 197 +13: [2022-12-02 10:52:42,831] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 111 +15: [2022-12-02 10:52:42,832] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 120 + 6: [2022-12-02 10:52:42,832] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 48 +26: [2022-12-02 10:52:42,833] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 209 +24: [2022-12-02 10:52:42,834] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 192 +22: [2022-12-02 10:52:42,834] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 177 +22: [2022-12-02 10:52:42,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-02 10:52:42,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 179 + 5: [2022-12-02 10:52:42,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,839] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 35 + 5: [2022-12-02 10:52:42,840] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 46 + 5: [2022-12-02 10:52:42,842] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 40 +22: [2022-12-02 10:52:42,842] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 181 +21: [2022-12-02 10:52:42,846] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 174 +26: [2022-12-02 10:52:42,848] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 213 + 4: [2022-12-02 10:52:42,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-02 10:52:42,851] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 38 +14: [2022-12-02 10:52:42,852] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 113 +29: [2022-12-02 10:52:42,853] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 236 +18: [2022-12-02 10:52:42,859] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 144 +20: [2022-12-02 10:52:42,860] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 167 + 6: [2022-12-02 10:52:42,860] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 50 + 5: [2022-12-02 10:52:42,861] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 44 +25: [2022-12-02 10:52:42,865] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 204 +27: [2022-12-02 10:52:42,866] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 221 +13: [2022-12-02 10:52:42,868] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 104 +26: [2022-12-02 10:52:42,869] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 208 +21: [2022-12-02 10:52:42,871] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 168 +11: [2022-12-02 10:52:42,872] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 94 +15: [2022-12-02 10:52:42,873] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 121 + 4: [2022-12-02 10:52:42,879] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 33 + 2: [2022-12-02 10:52:42,882] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 20 +15: [2022-12-02 10:52:42,882] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 122 +15: [2022-12-02 10:52:42,883] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 126 +18: [2022-12-02 10:52:42,884] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 148 +19: [2022-12-02 10:52:42,892] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 154 + 5: [2022-12-02 10:52:42,900] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 47 +18: [2022-12-02 10:52:42,900] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 149 +14: [2022-12-02 10:52:42,901] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 114 +18: [2022-12-02 10:52:42,902] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 151 +31: [2022-12-02 10:52:42,905] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 250 +28: [2022-12-02 10:52:42,906] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 226 +15: [2022-12-02 10:52:42,910] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 127 +29: [2022-12-02 10:52:42,910] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 238 +30: [2022-12-02 10:52:42,912] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 241 +22: [2022-12-02 10:52:42,912] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 179 +29: [2022-12-02 10:52:42,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_3b977b/global_step70000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-02 10:52:42,916] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 233 + 4: [2022-12-02 10:52:42,916] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 32 +31: [2022-12-02 10:52:42,928] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 252 +29: [2022-12-02 10:52:42,943] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 232 +11: [2022-12-02 10:52:42,950] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 88 + 4: [2022-12-02 10:52:42,954] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 37 +19: [2022-12-02 10:52:42,963] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 159 +25: [2022-12-02 10:52:42,963] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 200 +11: [2022-12-02 10:52:42,964] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 91 +22: [2022-12-02 10:52:42,968] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 178 +25: [2022-12-02 10:52:42,970] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 203 +31: [2022-12-02 10:52:42,975] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 249 +21: [2022-12-02 10:52:42,978] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 172 +11: [2022-12-02 10:52:42,980] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 93 + 5: [2022-12-02 10:52:42,986] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 46 +21: [2022-12-02 10:52:42,991] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 171 +19: [2022-12-02 10:52:42,992] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 157 +29: [2022-12-02 10:52:42,997] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 235 +21: [2022-12-02 10:52:43,010] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 173 +26: [2022-12-02 10:52:43,014] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 215 +30: [2022-12-02 10:52:43,028] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 247 + 5: [2022-12-02 10:52:43,029] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 42 +22: [2022-12-02 10:52:43,036] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 182 + 4: [2022-12-02 10:52:43,058] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 38 +29: [2022-12-02 10:52:43,073] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 233 +22: [2022-12-02 10:52:43,074] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 180 + 4: [2022-12-02 10:52:43,135] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 39 +25: [2022-12-02 10:52:43,253] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 205 + 0: successfully loaded checkpoint from checkpoints_3b977b at iteration 70000 +63: time (ms) | load-checkpoint: 14858.89 + 0: estimated model parameters: 4.05382912 + 0: estimated model parameters without embeddings: 3.745580544 + 0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-12-02 10:52:44 + 0: > building train, validation, and test datasets ... + 0: > datasets target sizes (minimum size): + 0: train: 37792969 + 0: validation: 37888 + 0: test: 512 + 0: > building train, validation, and test datasets for GPT ... + 0: > building dataset index ... + 0: reading sizes... + 0: reading pointers... + 0: reading document index... + 0: creating numpy buffer of mmap... + 0: creating memory view of numpy buffer... + 0: > finished creating indexed dataset in 0.033990 seconds + 0: number of documents: 210604984 + 0: > dataset split: + 0: train: + 0: document indices in [0, 199864130) total of 199864130 documents + 0: validation: + 0: document indices in [199864130, 210394379) total of 10530249 documents + 0: test: + 0: document indices in [210394379, 210604984) total of 210605 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_37792969ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_37792969ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_37792969ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.049 seconds + 0: total number of samples: 173377817 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_37888ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_37888ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_37888ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.093 seconds + 0: total number of samples: 9118345 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_512ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_512ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_512ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.087 seconds + 0: total number of samples: 182928 + 0: total number of epochs: 1 + 0: > finished creating GPT datasets ... + 0: [after dataloaders are built] datetime: 2022-12-02 10:53:11 + 0: done with setup ... + 0: training ... + 0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +63: time (ms) | model-and-optimizer-setup: 61007.62 | train/valid/test-data-iterators-setup: 26501.03 + 0: [000-000] 4.0538B / 3.7456B +32: [000-001] 4.0538B / 3.7456B + 0: [before the start of training step] datetime: 2022-12-02 10:53:11 + 0: [Rank 0] (after 70010 iterations) memory (MB) | allocated: 15589.80810546875 | max allocated: 46167.35498046875 | reserved: 49744.0 | max reserved: 49744.0 +63: iteration 70010/ 73814 | consumed samples: 35845120 | consumed tokens: 73410805760 | elapsed time per iteration (s): 11.63 | learning rate: 2.120E-05 | global batch size: 512 | lm loss: 1.800722E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 44.009 | TFLOPs: 4.53 | +32: [Rank 256] (after 70010 iterations) memory (MB) | allocated: 16405.80615234375 | max allocated: 32144.1962890625 | reserved: 38584.0 | max reserved: 38584.0 +63: iteration 70020/ 73814 | consumed samples: 35850240 | consumed tokens: 73421291520 | elapsed time per iteration (s): 2.32 | learning rate: 2.119E-05 | global batch size: 512 | lm loss: 1.802480E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.981 | TFLOPs: 22.75 | +63: iteration 70030/ 73814 | consumed samples: 35855360 | consumed tokens: 73431777280 | elapsed time per iteration (s): 2.23 | learning rate: 2.119E-05 | global batch size: 512 | lm loss: 1.791780E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.094 | TFLOPs: 23.58 | +63: iteration 70040/ 73814 | consumed samples: 35860480 | consumed tokens: 73442263040 | elapsed time per iteration (s): 2.24 | learning rate: 2.118E-05 | global batch size: 512 | lm loss: 1.805186E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.838 | TFLOPs: 23.56 | +63: iteration 70050/ 73814 | consumed samples: 35865600 | consumed tokens: 73452748800 | elapsed time per iteration (s): 2.24 | learning rate: 2.118E-05 | global batch size: 512 | lm loss: 1.810830E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.014 | TFLOPs: 23.58 | +63: iteration 70060/ 73814 | consumed samples: 35870720 | consumed tokens: 73463234560 | elapsed time per iteration (s): 2.22 | learning rate: 2.117E-05 | global batch size: 512 | lm loss: 1.822940E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.418 | TFLOPs: 23.72 | +63: iteration 70070/ 73814 | consumed samples: 35875840 | consumed tokens: 73473720320 | elapsed time per iteration (s): 2.25 | learning rate: 2.116E-05 | global batch size: 512 | lm loss: 1.802707E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.660 | TFLOPs: 23.44 | +63: iteration 70080/ 73814 | consumed samples: 35880960 | consumed tokens: 73484206080 | elapsed time per iteration (s): 2.23 | learning rate: 2.116E-05 | global batch size: 512 | lm loss: 1.803349E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.159 | TFLOPs: 23.59 | +63: iteration 70090/ 73814 | consumed samples: 35886080 | consumed tokens: 73494691840 | elapsed time per iteration (s): 2.23 | learning rate: 2.115E-05 | global batch size: 512 | lm loss: 1.813793E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.085 | TFLOPs: 23.69 | +63: iteration 70100/ 73814 | consumed samples: 35891200 | consumed tokens: 73505177600 | elapsed time per iteration (s): 2.25 | learning rate: 2.115E-05 | global batch size: 512 | lm loss: 1.793117E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.955 | TFLOPs: 23.47 | +63: iteration 70110/ 73814 | consumed samples: 35896320 | consumed tokens: 73515663360 | elapsed time per iteration (s): 2.25 | learning rate: 2.114E-05 | global batch size: 512 | lm loss: 1.777565E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.888 | TFLOPs: 23.46 | +63: iteration 70120/ 73814 | consumed samples: 35901440 | consumed tokens: 73526149120 | elapsed time per iteration (s): 2.24 | learning rate: 2.113E-05 | global batch size: 512 | lm loss: 1.788976E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.971 | TFLOPs: 23.57 | +63: iteration 70130/ 73814 | consumed samples: 35906560 | consumed tokens: 73536634880 | elapsed time per iteration (s): 2.23 | learning rate: 2.113E-05 | global batch size: 512 | lm loss: 1.794507E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.402 | TFLOPs: 23.62 | +63: iteration 70140/ 73814 | consumed samples: 35911680 | consumed tokens: 73547120640 | elapsed time per iteration (s): 2.23 | learning rate: 2.112E-05 | global batch size: 512 | lm loss: 1.802515E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.090 | TFLOPs: 23.69 | +63: iteration 70150/ 73814 | consumed samples: 35916800 | consumed tokens: 73557606400 | elapsed time per iteration (s): 2.23 | learning rate: 2.111E-05 | global batch size: 512 | lm loss: 1.818072E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.977 | TFLOPs: 23.68 | +63: iteration 70160/ 73814 | consumed samples: 35921920 | consumed tokens: 73568092160 | elapsed time per iteration (s): 2.24 | learning rate: 2.111E-05 | global batch size: 512 | lm loss: 1.816400E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.003 | TFLOPs: 23.57 | +63: iteration 70170/ 73814 | consumed samples: 35927040 | consumed tokens: 73578577920 | elapsed time per iteration (s): 2.24 | learning rate: 2.110E-05 | global batch size: 512 | lm loss: 1.803308E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.496 | TFLOPs: 23.52 | +63: iteration 70180/ 73814 | consumed samples: 35932160 | consumed tokens: 73589063680 | elapsed time per iteration (s): 2.23 | learning rate: 2.110E-05 | global batch size: 512 | lm loss: 1.791846E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.790 | TFLOPs: 23.66 | +63: iteration 70190/ 73814 | consumed samples: 35937280 | consumed tokens: 73599549440 | elapsed time per iteration (s): 2.22 | learning rate: 2.109E-05 | global batch size: 512 | lm loss: 1.803821E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.227 | TFLOPs: 23.70 | +63: iteration 70200/ 73814 | consumed samples: 35942400 | consumed tokens: 73610035200 | elapsed time per iteration (s): 2.23 | learning rate: 2.108E-05 | global batch size: 512 | lm loss: 1.801439E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.723 | TFLOPs: 23.65 | +63: iteration 70210/ 73814 | consumed samples: 35947520 | consumed tokens: 73620520960 | elapsed time per iteration (s): 2.23 | learning rate: 2.108E-05 | global batch size: 512 | lm loss: 1.797660E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.859 | TFLOPs: 23.66 | +63: iteration 70220/ 73814 | consumed samples: 35952640 | consumed tokens: 73631006720 | elapsed time per iteration (s): 2.23 | learning rate: 2.107E-05 | global batch size: 512 | lm loss: 1.786255E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.879 | TFLOPs: 23.66 | +63: iteration 70230/ 73814 | consumed samples: 35957760 | consumed tokens: 73641492480 | elapsed time per iteration (s): 2.23 | learning rate: 2.107E-05 | global batch size: 512 | lm loss: 1.810296E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.524 | TFLOPs: 23.63 | +63: iteration 70240/ 73814 | consumed samples: 35962880 | consumed tokens: 73651978240 | elapsed time per iteration (s): 2.26 | learning rate: 2.106E-05 | global batch size: 512 | lm loss: 1.801985E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.313 | TFLOPs: 23.30 | +63: iteration 70250/ 73814 | consumed samples: 35968000 | consumed tokens: 73662464000 | elapsed time per iteration (s): 2.23 | learning rate: 2.105E-05 | global batch size: 512 | lm loss: 1.805723E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.337 | TFLOPs: 23.61 | +63: iteration 70260/ 73814 | consumed samples: 35973120 | consumed tokens: 73672949760 | elapsed time per iteration (s): 2.23 | learning rate: 2.105E-05 | global batch size: 512 | lm loss: 1.801649E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.653 | TFLOPs: 23.64 | +63: iteration 70270/ 73814 | consumed samples: 35978240 | consumed tokens: 73683435520 | elapsed time per iteration (s): 2.22 | learning rate: 2.104E-05 | global batch size: 512 | lm loss: 1.816047E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.191 | TFLOPs: 23.70 | +63: iteration 70280/ 73814 | consumed samples: 35983360 | consumed tokens: 73693921280 | elapsed time per iteration (s): 2.23 | learning rate: 2.104E-05 | global batch size: 512 | lm loss: 1.802340E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 70290/ 73814 | consumed samples: 35988480 | consumed tokens: 73704407040 | elapsed time per iteration (s): 2.23 | learning rate: 2.103E-05 | global batch size: 512 | lm loss: 1.804125E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.531 | TFLOPs: 23.63 | +63: iteration 70300/ 73814 | consumed samples: 35993600 | consumed tokens: 73714892800 | elapsed time per iteration (s): 2.23 | learning rate: 2.103E-05 | global batch size: 512 | lm loss: 1.804868E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.157 | TFLOPs: 23.59 | +63: iteration 70310/ 73814 | consumed samples: 35998720 | consumed tokens: 73725378560 | elapsed time per iteration (s): 2.23 | learning rate: 2.102E-05 | global batch size: 512 | lm loss: 1.803337E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.347 | TFLOPs: 23.61 | +63: iteration 70320/ 73814 | consumed samples: 36003840 | consumed tokens: 73735864320 | elapsed time per iteration (s): 2.25 | learning rate: 2.101E-05 | global batch size: 512 | lm loss: 1.798642E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.322 | TFLOPs: 23.40 | +63: iteration 70330/ 73814 | consumed samples: 36008960 | consumed tokens: 73746350080 | elapsed time per iteration (s): 2.23 | learning rate: 2.101E-05 | global batch size: 512 | lm loss: 1.802490E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.109 | TFLOPs: 23.69 | +63: iteration 70340/ 73814 | consumed samples: 36014080 | consumed tokens: 73756835840 | elapsed time per iteration (s): 2.25 | learning rate: 2.100E-05 | global batch size: 512 | lm loss: 1.789818E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.721 | TFLOPs: 23.44 | +63: iteration 70350/ 73814 | consumed samples: 36019200 | consumed tokens: 73767321600 | elapsed time per iteration (s): 2.25 | learning rate: 2.100E-05 | global batch size: 512 | lm loss: 1.791019E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.163 | TFLOPs: 23.39 | +63: iteration 70360/ 73814 | consumed samples: 36024320 | consumed tokens: 73777807360 | elapsed time per iteration (s): 2.23 | learning rate: 2.099E-05 | global batch size: 512 | lm loss: 1.803275E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.954 | TFLOPs: 23.67 | +63: iteration 70370/ 73814 | consumed samples: 36029440 | consumed tokens: 73788293120 | elapsed time per iteration (s): 2.23 | learning rate: 2.098E-05 | global batch size: 512 | lm loss: 1.789975E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.220 | TFLOPs: 23.60 | +63: iteration 70380/ 73814 | consumed samples: 36034560 | consumed tokens: 73798778880 | elapsed time per iteration (s): 2.24 | learning rate: 2.098E-05 | global batch size: 512 | lm loss: 1.809043E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.214 | TFLOPs: 23.49 | +63: iteration 70390/ 73814 | consumed samples: 36039680 | consumed tokens: 73809264640 | elapsed time per iteration (s): 2.23 | learning rate: 2.097E-05 | global batch size: 512 | lm loss: 1.812267E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.662 | TFLOPs: 23.64 | +63: iteration 70400/ 73814 | consumed samples: 36044800 | consumed tokens: 73819750400 | elapsed time per iteration (s): 2.22 | learning rate: 2.097E-05 | global batch size: 512 | lm loss: 1.802289E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.116 | TFLOPs: 23.69 | +63: iteration 70410/ 73814 | consumed samples: 36049920 | consumed tokens: 73830236160 | elapsed time per iteration (s): 2.24 | learning rate: 2.096E-05 | global batch size: 512 | lm loss: 1.817763E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.126 | TFLOPs: 23.48 | +63: iteration 70420/ 73814 | consumed samples: 36055040 | consumed tokens: 73840721920 | elapsed time per iteration (s): 2.23 | learning rate: 2.096E-05 | global batch size: 512 | lm loss: 1.809561E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.582 | TFLOPs: 23.63 | +63: iteration 70430/ 73814 | consumed samples: 36060160 | consumed tokens: 73851207680 | elapsed time per iteration (s): 2.26 | learning rate: 2.095E-05 | global batch size: 512 | lm loss: 1.782813E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.725 | TFLOPs: 23.34 | +63: iteration 70440/ 73814 | consumed samples: 36065280 | consumed tokens: 73861693440 | elapsed time per iteration (s): 2.23 | learning rate: 2.095E-05 | global batch size: 512 | lm loss: 1.813289E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.631 | TFLOPs: 23.64 | +63: iteration 70450/ 73814 | consumed samples: 36070400 | consumed tokens: 73872179200 | elapsed time per iteration (s): 2.23 | learning rate: 2.094E-05 | global batch size: 512 | lm loss: 1.818336E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.343 | TFLOPs: 23.61 | +63: iteration 70460/ 73814 | consumed samples: 36075520 | consumed tokens: 73882664960 | elapsed time per iteration (s): 2.23 | learning rate: 2.093E-05 | global batch size: 512 | lm loss: 1.815788E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.042 | TFLOPs: 23.68 | +63: iteration 70470/ 73814 | consumed samples: 36080640 | consumed tokens: 73893150720 | elapsed time per iteration (s): 2.23 | learning rate: 2.093E-05 | global batch size: 512 | lm loss: 1.802190E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.939 | TFLOPs: 23.67 | +63: iteration 70480/ 73814 | consumed samples: 36085760 | consumed tokens: 73903636480 | elapsed time per iteration (s): 2.23 | learning rate: 2.092E-05 | global batch size: 512 | lm loss: 1.800236E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.698 | TFLOPs: 23.65 | +63: iteration 70490/ 73814 | consumed samples: 36090880 | consumed tokens: 73914122240 | elapsed time per iteration (s): 2.22 | learning rate: 2.092E-05 | global batch size: 512 | lm loss: 1.802357E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.144 | TFLOPs: 23.69 | +63: iteration 70500/ 73814 | consumed samples: 36096000 | consumed tokens: 73924608000 | elapsed time per iteration (s): 2.23 | learning rate: 2.091E-05 | global batch size: 512 | lm loss: 1.807903E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.830 | TFLOPs: 23.66 | +63: iteration 70510/ 73814 | consumed samples: 36101120 | consumed tokens: 73935093760 | elapsed time per iteration (s): 2.23 | learning rate: 2.091E-05 | global batch size: 512 | lm loss: 1.803620E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.048 | TFLOPs: 23.68 | +63: iteration 70520/ 73814 | consumed samples: 36106240 | consumed tokens: 73945579520 | elapsed time per iteration (s): 2.23 | learning rate: 2.090E-05 | global batch size: 512 | lm loss: 1.770752E+00 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 70530/ 73814 | consumed samples: 36111360 | consumed tokens: 73956065280 | elapsed time per iteration (s): 2.23 | learning rate: 2.090E-05 | global batch size: 512 | lm loss: 1.829818E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.992 | TFLOPs: 23.68 | +63: iteration 70540/ 73814 | consumed samples: 36116480 | consumed tokens: 73966551040 | elapsed time per iteration (s): 2.25 | learning rate: 2.089E-05 | global batch size: 512 | lm loss: 1.803906E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.739 | TFLOPs: 23.44 | +63: iteration 70550/ 73814 | consumed samples: 36121600 | consumed tokens: 73977036800 | elapsed time per iteration (s): 2.22 | learning rate: 2.088E-05 | global batch size: 512 | lm loss: 1.823614E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.162 | TFLOPs: 23.69 | +63: iteration 70560/ 73814 | consumed samples: 36126720 | consumed tokens: 73987522560 | elapsed time per iteration (s): 2.23 | learning rate: 2.088E-05 | global batch size: 512 | lm loss: 1.814765E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.545 | TFLOPs: 23.63 | +63: iteration 70570/ 73814 | consumed samples: 36131840 | consumed tokens: 73998008320 | elapsed time per iteration (s): 2.25 | learning rate: 2.087E-05 | global batch size: 512 | lm loss: 1.786434E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.996 | TFLOPs: 23.47 | +63: iteration 70580/ 73814 | consumed samples: 36136960 | consumed tokens: 74008494080 | elapsed time per iteration (s): 2.22 | learning rate: 2.087E-05 | global batch size: 512 | lm loss: 1.804823E+00 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.172 | TFLOPs: 23.70 | +63: iteration 70590/ 73814 | consumed samples: 36142080 | consumed tokens: 74018979840 | elapsed time per iteration (s): 2.24 | learning rate: 2.086E-05 | global batch size: 512 | lm loss: 1.804753E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.616 | TFLOPs: 23.53 | +63: iteration 70600/ 73814 | consumed samples: 36147200 | consumed tokens: 74029465600 | elapsed time per iteration (s): 2.25 | learning rate: 2.086E-05 | global batch size: 512 | lm loss: 1.812701E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.517 | TFLOPs: 23.42 | +63: iteration 70610/ 73814 | consumed samples: 36152320 | consumed tokens: 74039951360 | elapsed time per iteration (s): 2.23 | learning rate: 2.085E-05 | global batch size: 512 | lm loss: 1.802410E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.550 | TFLOPs: 23.63 | +63: iteration 70620/ 73814 | consumed samples: 36157440 | consumed tokens: 74050437120 | elapsed time per iteration (s): 2.22 | learning rate: 2.085E-05 | global batch size: 512 | lm loss: 1.809156E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.295 | TFLOPs: 23.71 | +63: iteration 70630/ 73814 | consumed samples: 36162560 | consumed tokens: 74060922880 | elapsed time per iteration (s): 2.23 | learning rate: 2.084E-05 | global batch size: 512 | lm loss: 1.814782E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.928 | TFLOPs: 23.67 | +63: iteration 70640/ 73814 | consumed samples: 36167680 | consumed tokens: 74071408640 | elapsed time per iteration (s): 2.23 | learning rate: 2.084E-05 | global batch size: 512 | lm loss: 1.810354E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.106 | TFLOPs: 23.69 | +63: iteration 70650/ 73814 | consumed samples: 36172800 | consumed tokens: 74081894400 | elapsed time per iteration (s): 2.25 | learning rate: 2.083E-05 | global batch size: 512 | lm loss: 1.819770E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.932 | TFLOPs: 23.46 | +63: iteration 70660/ 73814 | consumed samples: 36177920 | consumed tokens: 74092380160 | elapsed time per iteration (s): 2.23 | learning rate: 2.083E-05 | global batch size: 512 | lm loss: 1.805632E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.071 | TFLOPs: 23.68 | +63: iteration 70670/ 73814 | consumed samples: 36183040 | consumed tokens: 74102865920 | elapsed time per iteration (s): 2.22 | learning rate: 2.082E-05 | global batch size: 512 | lm loss: 1.813163E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.307 | TFLOPs: 23.71 | +63: iteration 70680/ 73814 | consumed samples: 36188160 | consumed tokens: 74113351680 | elapsed time per iteration (s): 2.22 | learning rate: 2.082E-05 | global batch size: 512 | lm loss: 1.788984E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.181 | TFLOPs: 23.70 | +63: iteration 70690/ 73814 | consumed samples: 36193280 | consumed tokens: 74123837440 | elapsed time per iteration (s): 2.23 | learning rate: 2.081E-05 | global batch size: 512 | lm loss: 1.805089E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.797 | TFLOPs: 23.66 | +63: iteration 70700/ 73814 | consumed samples: 36198400 | consumed tokens: 74134323200 | elapsed time per iteration (s): 2.23 | learning rate: 2.081E-05 | global batch size: 512 | lm loss: 1.799956E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.793 | TFLOPs: 23.66 | +63: iteration 70710/ 73814 | consumed samples: 36203520 | consumed tokens: 74144808960 | elapsed time per iteration (s): 2.23 | learning rate: 2.080E-05 | global batch size: 512 | lm loss: 1.803334E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.857 | TFLOPs: 23.66 | +63: iteration 70720/ 73814 | consumed samples: 36208640 | consumed tokens: 74155294720 | elapsed time per iteration (s): 2.23 | learning rate: 2.080E-05 | global batch size: 512 | lm loss: 1.775316E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.100 | TFLOPs: 23.69 | +63: iteration 70730/ 73814 | consumed samples: 36213760 | consumed tokens: 74165780480 | elapsed time per iteration (s): 2.22 | learning rate: 2.079E-05 | global batch size: 512 | lm loss: 1.816560E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.316 | TFLOPs: 23.71 | +63: iteration 70740/ 73814 | consumed samples: 36218880 | consumed tokens: 74176266240 | elapsed time per iteration (s): 2.24 | learning rate: 2.078E-05 | global batch size: 512 | lm loss: 1.810736E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.326 | TFLOPs: 23.51 | +63: iteration 70750/ 73814 | consumed samples: 36224000 | consumed tokens: 74186752000 | elapsed time per iteration (s): 2.23 | learning rate: 2.078E-05 | global batch size: 512 | lm loss: 1.802817E+00 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.750 | TFLOPs: 23.65 | +63: iteration 70760/ 73814 | consumed samples: 36229120 | consumed tokens: 74197237760 | elapsed time per iteration (s): 2.25 | learning rate: 2.077E-05 | global batch size: 512 | lm loss: 1.800807E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.457 | TFLOPs: 23.42 | +63: iteration 70770/ 73814 | consumed samples: 36234240 | consumed tokens: 74207723520 | elapsed time per iteration (s): 2.23 | learning rate: 2.077E-05 | global batch size: 512 | lm loss: 1.805162E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.840 | TFLOPs: 23.66 | +63: iteration 70780/ 73814 | consumed samples: 36239360 | consumed tokens: 74218209280 | elapsed time per iteration (s): 2.25 | learning rate: 2.076E-05 | global batch size: 512 | lm loss: 1.779540E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.978 | TFLOPs: 23.47 | +63: iteration 70790/ 73814 | consumed samples: 36244480 | consumed tokens: 74228695040 | elapsed time per iteration (s): 2.23 | learning rate: 2.076E-05 | global batch size: 512 | lm loss: 1.806973E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.584 | TFLOPs: 23.63 | +63: iteration 70800/ 73814 | consumed samples: 36249600 | consumed tokens: 74239180800 | elapsed time per iteration (s): 2.24 | learning rate: 2.075E-05 | global batch size: 512 | lm loss: 1.805188E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.835 | TFLOPs: 23.56 | +63: iteration 70810/ 73814 | consumed samples: 36254720 | consumed tokens: 74249666560 | elapsed time per iteration (s): 2.23 | learning rate: 2.075E-05 | global batch size: 512 | lm loss: 1.809277E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.921 | TFLOPs: 23.67 | +63: iteration 70820/ 73814 | consumed samples: 36259840 | consumed tokens: 74260152320 | elapsed time per iteration (s): 2.23 | learning rate: 2.074E-05 | global batch size: 512 | lm loss: 1.817009E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.549 | TFLOPs: 23.63 | +63: iteration 70830/ 73814 | consumed samples: 36264960 | consumed tokens: 74270638080 | elapsed time per iteration (s): 2.25 | learning rate: 2.074E-05 | global batch size: 512 | lm loss: 1.808200E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.668 | TFLOPs: 23.44 | +63: iteration 70840/ 73814 | consumed samples: 36270080 | consumed tokens: 74281123840 | elapsed time per iteration (s): 2.25 | learning rate: 2.073E-05 | global batch size: 512 | lm loss: 1.804436E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.386 | TFLOPs: 23.41 | +63: iteration 70850/ 73814 | consumed samples: 36275200 | consumed tokens: 74291609600 | elapsed time per iteration (s): 2.27 | learning rate: 2.073E-05 | global batch size: 512 | lm loss: 1.788066E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.536 | TFLOPs: 23.22 | +63: iteration 70860/ 73814 | consumed samples: 36280320 | consumed tokens: 74302095360 | elapsed time per iteration (s): 2.22 | learning rate: 2.072E-05 | global batch size: 512 | lm loss: 1.794578E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.152 | TFLOPs: 23.69 | +63: iteration 70870/ 73814 | consumed samples: 36285440 | consumed tokens: 74312581120 | elapsed time per iteration (s): 2.23 | learning rate: 2.072E-05 | global batch size: 512 | lm loss: 1.780719E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.555 | TFLOPs: 23.63 | +63: iteration 70880/ 73814 | consumed samples: 36290560 | consumed tokens: 74323066880 | elapsed time per iteration (s): 2.25 | learning rate: 2.072E-05 | global batch size: 512 | lm loss: 1.808393E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.059 | TFLOPs: 23.37 | +63: iteration 70890/ 73814 | consumed samples: 36295680 | consumed tokens: 74333552640 | elapsed time per iteration (s): 2.23 | learning rate: 2.071E-05 | global batch size: 512 | lm loss: 1.812559E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.622 | TFLOPs: 23.64 | +63: iteration 70900/ 73814 | consumed samples: 36300800 | consumed tokens: 74344038400 | elapsed time per iteration (s): 2.23 | learning rate: 2.071E-05 | global batch size: 512 | lm loss: 1.796084E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.167 | TFLOPs: 23.59 | +63: iteration 70910/ 73814 | consumed samples: 36305920 | consumed tokens: 74354524160 | elapsed time per iteration (s): 2.27 | learning rate: 2.070E-05 | global batch size: 512 | lm loss: 1.808820E+00 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.608 | TFLOPs: 23.23 | +63: iteration 70920/ 73814 | consumed samples: 36311040 | consumed tokens: 74365009920 | elapsed time per iteration (s): 2.33 | learning rate: 2.070E-05 | global batch size: 512 | lm loss: 1.805631E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.493 | TFLOPs: 22.60 | +63: iteration 70930/ 73814 | consumed samples: 36316160 | consumed tokens: 74375495680 | elapsed time per iteration (s): 2.24 | learning rate: 2.069E-05 | global batch size: 512 | lm loss: 1.831030E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.723 | TFLOPs: 23.55 | +63: iteration 70940/ 73814 | consumed samples: 36321280 | consumed tokens: 74385981440 | elapsed time per iteration (s): 2.25 | learning rate: 2.069E-05 | global batch size: 512 | lm loss: 1.826369E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.000 | TFLOPs: 23.47 | +63: iteration 70950/ 73814 | consumed samples: 36326400 | consumed tokens: 74396467200 | elapsed time per iteration (s): 2.23 | learning rate: 2.068E-05 | global batch size: 512 | lm loss: 1.802640E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.432 | TFLOPs: 23.62 | +63: iteration 70960/ 73814 | consumed samples: 36331520 | consumed tokens: 74406952960 | elapsed time per iteration (s): 2.24 | learning rate: 2.068E-05 | global batch size: 512 | lm loss: 1.811794E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.331 | TFLOPs: 23.51 | +63: iteration 70970/ 73814 | consumed samples: 36336640 | consumed tokens: 74417438720 | elapsed time per iteration (s): 2.27 | learning rate: 2.067E-05 | global batch size: 512 | lm loss: 1.791736E+00 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.738 | TFLOPs: 23.24 | +63: iteration 70980/ 73814 | consumed samples: 36341760 | consumed tokens: 74427924480 | elapsed time per iteration (s): 2.26 | learning rate: 2.067E-05 | global batch size: 512 | lm loss: 1.817526E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.913 | TFLOPs: 23.36 | +63: iteration 70990/ 73814 | consumed samples: 36346880 | consumed tokens: 74438410240 | elapsed time per iteration (s): 2.25 | learning rate: 2.066E-05 | global batch size: 512 | lm loss: 1.804962E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.260 | TFLOPs: 23.40 | +63: iteration 71000/ 73814 | consumed samples: 36352000 | consumed tokens: 74448896000 | elapsed time per iteration (s): 2.27 | learning rate: 2.066E-05 | global batch size: 512 | lm loss: 1.809898E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.452 | TFLOPs: 23.21 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 71000 | lm loss value: 1.775514E+00 | lm loss PPL: 5.903318E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 71010/ 73814 | consumed samples: 36357120 | consumed tokens: 74459381760 | elapsed time per iteration (s): 2.30 | learning rate: 2.065E-05 | global batch size: 512 | lm loss: 1.789458E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.492 | TFLOPs: 22.90 | +63: iteration 71020/ 73814 | consumed samples: 36362240 | consumed tokens: 74469867520 | elapsed time per iteration (s): 2.23 | learning rate: 2.065E-05 | global batch size: 512 | lm loss: 1.805091E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.716 | TFLOPs: 23.65 | +63: iteration 71030/ 73814 | consumed samples: 36367360 | consumed tokens: 74480353280 | elapsed time per iteration (s): 2.23 | learning rate: 2.064E-05 | global batch size: 512 | lm loss: 1.810065E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.132 | TFLOPs: 23.59 | +63: iteration 71040/ 73814 | consumed samples: 36372480 | consumed tokens: 74490839040 | elapsed time per iteration (s): 2.27 | learning rate: 2.064E-05 | global batch size: 512 | lm loss: 1.800649E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.663 | TFLOPs: 23.23 | +63: iteration 71050/ 73814 | consumed samples: 36377600 | consumed tokens: 74501324800 | elapsed time per iteration (s): 2.24 | learning rate: 2.063E-05 | global batch size: 512 | lm loss: 1.801917E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.888 | TFLOPs: 23.56 | +63: iteration 71060/ 73814 | consumed samples: 36382720 | consumed tokens: 74511810560 | elapsed time per iteration (s): 2.25 | learning rate: 2.063E-05 | global batch size: 512 | lm loss: 1.790611E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.110 | TFLOPs: 23.38 | +63: iteration 71070/ 73814 | consumed samples: 36387840 | consumed tokens: 74522296320 | elapsed time per iteration (s): 2.22 | learning rate: 2.063E-05 | global batch size: 512 | lm loss: 1.799945E+00 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.252 | TFLOPs: 23.70 | +63: iteration 71080/ 73814 | consumed samples: 36392960 | consumed tokens: 74532782080 | elapsed time per iteration (s): 2.23 | learning rate: 2.062E-05 | global batch size: 512 | lm loss: 1.804688E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.014 | TFLOPs: 23.68 | +63: iteration 71090/ 73814 | consumed samples: 36398080 | consumed tokens: 74543267840 | elapsed time per iteration (s): 2.26 | learning rate: 2.062E-05 | global batch size: 512 | lm loss: 1.823431E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.691 | TFLOPs: 23.34 | +63: iteration 71100/ 73814 | consumed samples: 36403200 | consumed tokens: 74553753600 | elapsed time per iteration (s): 2.23 | learning rate: 2.061E-05 | global batch size: 512 | lm loss: 1.807049E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.678 | TFLOPs: 23.64 | +63: iteration 71110/ 73814 | consumed samples: 36408320 | consumed tokens: 74564239360 | elapsed time per iteration (s): 2.25 | learning rate: 2.061E-05 | global batch size: 512 | lm loss: 1.812865E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.964 | TFLOPs: 23.47 | +63: iteration 71120/ 73814 | consumed samples: 36413440 | consumed tokens: 74574725120 | elapsed time per iteration (s): 2.24 | learning rate: 2.060E-05 | global batch size: 512 | lm loss: 1.812345E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.338 | TFLOPs: 23.51 | +63: iteration 71130/ 73814 | consumed samples: 36418560 | consumed tokens: 74585210880 | elapsed time per iteration (s): 2.23 | learning rate: 2.060E-05 | global batch size: 512 | lm loss: 1.814960E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.855 | TFLOPs: 23.66 | +63: iteration 71140/ 73814 | consumed samples: 36423680 | consumed tokens: 74595696640 | elapsed time per iteration (s): 2.25 | learning rate: 2.059E-05 | global batch size: 512 | lm loss: 1.787928E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.658 | TFLOPs: 23.44 | +63: iteration 71150/ 73814 | consumed samples: 36428800 | consumed tokens: 74606182400 | elapsed time per iteration (s): 2.24 | learning rate: 2.059E-05 | global batch size: 512 | lm loss: 1.801591E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.052 | TFLOPs: 23.58 | +63: iteration 71160/ 73814 | consumed samples: 36433920 | consumed tokens: 74616668160 | elapsed time per iteration (s): 2.27 | learning rate: 2.059E-05 | global batch size: 512 | lm loss: 1.815704E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.739 | TFLOPs: 23.24 | +63: iteration 71170/ 73814 | consumed samples: 36439040 | consumed tokens: 74627153920 | elapsed time per iteration (s): 2.24 | learning rate: 2.058E-05 | global batch size: 512 | lm loss: 1.794396E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.471 | TFLOPs: 23.52 | +63: iteration 71180/ 73814 | consumed samples: 36444160 | consumed tokens: 74637639680 | elapsed time per iteration (s): 2.24 | learning rate: 2.058E-05 | global batch size: 512 | lm loss: 1.811744E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.687 | TFLOPs: 23.54 | +63: iteration 71190/ 73814 | consumed samples: 36449280 | consumed tokens: 74648125440 | elapsed time per iteration (s): 2.28 | learning rate: 2.057E-05 | global batch size: 512 | lm loss: 1.798206E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.721 | TFLOPs: 23.13 | +63: iteration 71200/ 73814 | consumed samples: 36454400 | consumed tokens: 74658611200 | elapsed time per iteration (s): 2.24 | learning rate: 2.057E-05 | global batch size: 512 | lm loss: 1.794717E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.036 | TFLOPs: 23.58 | +63: iteration 71210/ 73814 | consumed samples: 36459520 | consumed tokens: 74669096960 | elapsed time per iteration (s): 2.23 | learning rate: 2.056E-05 | global batch size: 512 | lm loss: 1.802141E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.853 | TFLOPs: 23.66 | +63: iteration 71220/ 73814 | consumed samples: 36464640 | consumed tokens: 74679582720 | elapsed time per iteration (s): 2.23 | learning rate: 2.056E-05 | global batch size: 512 | lm loss: 1.799014E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.132 | TFLOPs: 23.59 | +63: iteration 71230/ 73814 | consumed samples: 36469760 | consumed tokens: 74690068480 | elapsed time per iteration (s): 2.25 | learning rate: 2.055E-05 | global batch size: 512 | lm loss: 1.808510E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.067 | TFLOPs: 23.38 | +63: iteration 71240/ 73814 | consumed samples: 36474880 | consumed tokens: 74700554240 | elapsed time per iteration (s): 2.26 | learning rate: 2.055E-05 | global batch size: 512 | lm loss: 1.807277E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.221 | TFLOPs: 23.29 | +63: iteration 71250/ 73814 | consumed samples: 36480000 | consumed tokens: 74711040000 | elapsed time per iteration (s): 2.25 | learning rate: 2.055E-05 | global batch size: 512 | lm loss: 1.801021E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.810 | TFLOPs: 23.45 | +63: iteration 71260/ 73814 | consumed samples: 36485120 | consumed tokens: 74721525760 | elapsed time per iteration (s): 2.26 | learning rate: 2.054E-05 | global batch size: 512 | lm loss: 1.802359E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.800 | TFLOPs: 23.35 | +63: iteration 71270/ 73814 | consumed samples: 36490240 | consumed tokens: 74732011520 | elapsed time per iteration (s): 2.26 | learning rate: 2.054E-05 | global batch size: 512 | lm loss: 1.806876E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.560 | TFLOPs: 23.32 | +63: iteration 71280/ 73814 | consumed samples: 36495360 | consumed tokens: 74742497280 | elapsed time per iteration (s): 2.30 | learning rate: 2.053E-05 | global batch size: 512 | lm loss: 1.802548E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.280 | TFLOPs: 22.88 | +63: iteration 71290/ 73814 | consumed samples: 36500480 | consumed tokens: 74752983040 | elapsed time per iteration (s): 2.28 | learning rate: 2.053E-05 | global batch size: 512 | lm loss: 1.796700E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.025 | TFLOPs: 23.17 | +63: iteration 71300/ 73814 | consumed samples: 36505600 | consumed tokens: 74763468800 | elapsed time per iteration (s): 2.24 | learning rate: 2.053E-05 | global batch size: 512 | lm loss: 1.815922E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.470 | TFLOPs: 23.52 | +63: iteration 71310/ 73814 | consumed samples: 36510720 | consumed tokens: 74773954560 | elapsed time per iteration (s): 2.25 | learning rate: 2.052E-05 | global batch size: 512 | lm loss: 1.811797E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.645 | TFLOPs: 23.43 | +63: iteration 71320/ 73814 | consumed samples: 36515840 | consumed tokens: 74784440320 | elapsed time per iteration (s): 2.25 | learning rate: 2.052E-05 | global batch size: 512 | lm loss: 1.794720E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.321 | TFLOPs: 23.40 | +63: iteration 71330/ 73814 | consumed samples: 36520960 | consumed tokens: 74794926080 | elapsed time per iteration (s): 2.23 | learning rate: 2.051E-05 | global batch size: 512 | lm loss: 1.800060E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.198 | TFLOPs: 23.59 | +63: iteration 71340/ 73814 | consumed samples: 36526080 | consumed tokens: 74805411840 | elapsed time per iteration (s): 2.26 | learning rate: 2.051E-05 | global batch size: 512 | lm loss: 1.804404E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.957 | TFLOPs: 23.36 | +63: iteration 71350/ 73814 | consumed samples: 36531200 | consumed tokens: 74815897600 | elapsed time per iteration (s): 2.24 | learning rate: 2.050E-05 | global batch size: 512 | lm loss: 1.815420E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.614 | TFLOPs: 23.53 | +63: iteration 71360/ 73814 | consumed samples: 36536320 | consumed tokens: 74826383360 | elapsed time per iteration (s): 2.24 | learning rate: 2.050E-05 | global batch size: 512 | lm loss: 1.815191E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.969 | TFLOPs: 23.57 | +63: iteration 71370/ 73814 | consumed samples: 36541440 | consumed tokens: 74836869120 | elapsed time per iteration (s): 2.26 | learning rate: 2.050E-05 | global batch size: 512 | lm loss: 1.809431E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.534 | TFLOPs: 23.32 | +63: iteration 71380/ 73814 | consumed samples: 36546560 | consumed tokens: 74847354880 | elapsed time per iteration (s): 2.25 | learning rate: 2.049E-05 | global batch size: 512 | lm loss: 1.789258E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.969 | TFLOPs: 23.47 | +63: iteration 71390/ 73814 | consumed samples: 36551680 | consumed tokens: 74857840640 | elapsed time per iteration (s): 2.23 | learning rate: 2.049E-05 | global batch size: 512 | lm loss: 1.787211E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 71400/ 73814 | consumed samples: 36556800 | consumed tokens: 74868326400 | elapsed time per iteration (s): 2.24 | learning rate: 2.048E-05 | global batch size: 512 | lm loss: 1.807565E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.258 | TFLOPs: 23.50 | +63: iteration 71410/ 73814 | consumed samples: 36561920 | consumed tokens: 74878812160 | elapsed time per iteration (s): 2.23 | learning rate: 2.048E-05 | global batch size: 512 | lm loss: 1.799747E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.787 | TFLOPs: 23.66 | +63: iteration 71420/ 73814 | consumed samples: 36567040 | consumed tokens: 74889297920 | elapsed time per iteration (s): 2.22 | learning rate: 2.048E-05 | global batch size: 512 | lm loss: 1.802064E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.170 | TFLOPs: 23.69 | +63: iteration 71430/ 73814 | consumed samples: 36572160 | consumed tokens: 74899783680 | elapsed time per iteration (s): 2.24 | learning rate: 2.047E-05 | global batch size: 512 | lm loss: 1.795453E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.731 | TFLOPs: 23.55 | +63: iteration 71440/ 73814 | consumed samples: 36577280 | consumed tokens: 74910269440 | elapsed time per iteration (s): 2.61 | learning rate: 2.047E-05 | global batch size: 512 | lm loss: 1.807195E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 195.945 | TFLOPs: 20.17 | +63: iteration 71450/ 73814 | consumed samples: 36582400 | consumed tokens: 74920755200 | elapsed time per iteration (s): 2.39 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 1.794950E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.604 | TFLOPs: 22.09 | +63: iteration 71460/ 73814 | consumed samples: 36587520 | consumed tokens: 74931240960 | elapsed time per iteration (s): 2.23 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 1.805956E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.744 | TFLOPs: 23.65 | +63: iteration 71470/ 73814 | consumed samples: 36592640 | consumed tokens: 74941726720 | elapsed time per iteration (s): 2.54 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 1.795046E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.303 | TFLOPs: 20.72 | +63: iteration 71480/ 73814 | consumed samples: 36597760 | consumed tokens: 74952212480 | elapsed time per iteration (s): 2.24 | learning rate: 2.045E-05 | global batch size: 512 | lm loss: 1.803315E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.959 | TFLOPs: 23.57 | +63: iteration 71490/ 73814 | consumed samples: 36602880 | consumed tokens: 74962698240 | elapsed time per iteration (s): 2.25 | learning rate: 2.045E-05 | global batch size: 512 | lm loss: 1.805712E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.640 | TFLOPs: 23.43 | +63: iteration 71500/ 73814 | consumed samples: 36608000 | consumed tokens: 74973184000 | elapsed time per iteration (s): 2.23 | learning rate: 2.045E-05 | global batch size: 512 | lm loss: 1.821523E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.710 | TFLOPs: 23.65 | +63: iteration 71510/ 73814 | consumed samples: 36613120 | consumed tokens: 74983669760 | elapsed time per iteration (s): 2.57 | learning rate: 2.044E-05 | global batch size: 512 | lm loss: 1.811982E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 199.261 | TFLOPs: 20.51 | +63: iteration 71520/ 73814 | consumed samples: 36618240 | consumed tokens: 74994155520 | elapsed time per iteration (s): 2.24 | learning rate: 2.044E-05 | global batch size: 512 | lm loss: 1.829472E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.119 | TFLOPs: 23.48 | +63: iteration 71530/ 73814 | consumed samples: 36623360 | consumed tokens: 75004641280 | elapsed time per iteration (s): 2.26 | learning rate: 2.043E-05 | global batch size: 512 | lm loss: 1.786709E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.825 | TFLOPs: 23.35 | +63: iteration 71540/ 73814 | consumed samples: 36628480 | consumed tokens: 75015127040 | elapsed time per iteration (s): 2.25 | learning rate: 2.043E-05 | global batch size: 512 | lm loss: 1.805269E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.641 | TFLOPs: 23.43 | +63: iteration 71550/ 73814 | consumed samples: 36633600 | consumed tokens: 75025612800 | elapsed time per iteration (s): 2.24 | learning rate: 2.043E-05 | global batch size: 512 | lm loss: 1.797175E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.886 | TFLOPs: 23.56 | +63: iteration 71560/ 73814 | consumed samples: 36638720 | consumed tokens: 75036098560 | elapsed time per iteration (s): 2.29 | learning rate: 2.042E-05 | global batch size: 512 | lm loss: 1.797885E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.918 | TFLOPs: 23.05 | +63: iteration 71570/ 73814 | consumed samples: 36643840 | consumed tokens: 75046584320 | elapsed time per iteration (s): 2.29 | learning rate: 2.042E-05 | global batch size: 512 | lm loss: 1.787979E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.417 | TFLOPs: 23.00 | +63: iteration 71580/ 73814 | consumed samples: 36648960 | consumed tokens: 75057070080 | elapsed time per iteration (s): 2.32 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 1.793406E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.130 | TFLOPs: 22.76 | +63: iteration 71590/ 73814 | consumed samples: 36654080 | consumed tokens: 75067555840 | elapsed time per iteration (s): 2.38 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 1.787842E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 215.296 | TFLOPs: 22.16 | +63: iteration 71600/ 73814 | consumed samples: 36659200 | consumed tokens: 75078041600 | elapsed time per iteration (s): 2.33 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 1.808588E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.994 | TFLOPs: 22.65 | +63: iteration 71610/ 73814 | consumed samples: 36664320 | consumed tokens: 75088527360 | elapsed time per iteration (s): 2.27 | learning rate: 2.040E-05 | global batch size: 512 | lm loss: 1.803663E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.630 | TFLOPs: 23.23 | +63: iteration 71620/ 73814 | consumed samples: 36669440 | consumed tokens: 75099013120 | elapsed time per iteration (s): 2.25 | learning rate: 2.040E-05 | global batch size: 512 | lm loss: 1.794056E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.316 | TFLOPs: 23.40 | +63: iteration 71630/ 73814 | consumed samples: 36674560 | consumed tokens: 75109498880 | elapsed time per iteration (s): 2.24 | learning rate: 2.040E-05 | global batch size: 512 | lm loss: 1.805309E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.351 | TFLOPs: 23.51 | +63: iteration 71640/ 73814 | consumed samples: 36679680 | consumed tokens: 75119984640 | elapsed time per iteration (s): 2.23 | learning rate: 2.039E-05 | global batch size: 512 | lm loss: 1.804308E+00 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.736 | TFLOPs: 23.65 | +63: iteration 71650/ 73814 | consumed samples: 36684800 | consumed tokens: 75130470400 | elapsed time per iteration (s): 2.24 | learning rate: 2.039E-05 | global batch size: 512 | lm loss: 1.813922E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.360 | TFLOPs: 23.51 | +63: iteration 71660/ 73814 | consumed samples: 36689920 | consumed tokens: 75140956160 | elapsed time per iteration (s): 2.24 | learning rate: 2.039E-05 | global batch size: 512 | lm loss: 1.785375E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.798 | TFLOPs: 23.55 | +63: iteration 71670/ 73814 | consumed samples: 36695040 | consumed tokens: 75151441920 | elapsed time per iteration (s): 2.24 | learning rate: 2.038E-05 | global batch size: 512 | lm loss: 1.808800E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.835 | TFLOPs: 23.56 | +63: iteration 71680/ 73814 | consumed samples: 36700160 | consumed tokens: 75161927680 | elapsed time per iteration (s): 2.25 | learning rate: 2.038E-05 | global batch size: 512 | lm loss: 1.786597E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.080 | TFLOPs: 23.38 | +63: iteration 71690/ 73814 | consumed samples: 36705280 | consumed tokens: 75172413440 | elapsed time per iteration (s): 2.37 | learning rate: 2.038E-05 | global batch size: 512 | lm loss: 1.803869E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.373 | TFLOPs: 22.27 | +63: iteration 71700/ 73814 | consumed samples: 36710400 | consumed tokens: 75182899200 | elapsed time per iteration (s): 2.43 | learning rate: 2.037E-05 | global batch size: 512 | lm loss: 1.808358E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 210.888 | TFLOPs: 21.71 | +63: iteration 71710/ 73814 | consumed samples: 36715520 | consumed tokens: 75193384960 | elapsed time per iteration (s): 2.24 | learning rate: 2.037E-05 | global batch size: 512 | lm loss: 1.805741E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.228 | TFLOPs: 23.49 | +63: iteration 71720/ 73814 | consumed samples: 36720640 | consumed tokens: 75203870720 | elapsed time per iteration (s): 2.23 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.800965E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.854 | TFLOPs: 23.66 | +63: iteration 71730/ 73814 | consumed samples: 36725760 | consumed tokens: 75214356480 | elapsed time per iteration (s): 2.25 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.812777E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.994 | TFLOPs: 23.47 | +63: iteration 71740/ 73814 | consumed samples: 36730880 | consumed tokens: 75224842240 | elapsed time per iteration (s): 2.25 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.825750E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.075 | TFLOPs: 23.38 | +63: iteration 71750/ 73814 | consumed samples: 36736000 | consumed tokens: 75235328000 | elapsed time per iteration (s): 2.28 | learning rate: 2.035E-05 | global batch size: 512 | lm loss: 1.802969E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.106 | TFLOPs: 23.07 | +63: iteration 71760/ 73814 | consumed samples: 36741120 | consumed tokens: 75245813760 | elapsed time per iteration (s): 2.24 | learning rate: 2.035E-05 | global batch size: 512 | lm loss: 1.802978E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.698 | TFLOPs: 23.54 | +63: iteration 71770/ 73814 | consumed samples: 36746240 | consumed tokens: 75256299520 | elapsed time per iteration (s): 2.24 | learning rate: 2.035E-05 | global batch size: 512 | lm loss: 1.790854E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.891 | TFLOPs: 23.56 | +63: iteration 71780/ 73814 | consumed samples: 36751360 | consumed tokens: 75266785280 | elapsed time per iteration (s): 2.23 | learning rate: 2.034E-05 | global batch size: 512 | lm loss: 1.799038E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.619 | TFLOPs: 23.64 | +63: iteration 71790/ 73814 | consumed samples: 36756480 | consumed tokens: 75277271040 | elapsed time per iteration (s): 2.22 | learning rate: 2.034E-05 | global batch size: 512 | lm loss: 1.833353E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.120 | TFLOPs: 23.69 | +63: iteration 71800/ 73814 | consumed samples: 36761600 | consumed tokens: 75287756800 | elapsed time per iteration (s): 2.25 | learning rate: 2.034E-05 | global batch size: 512 | lm loss: 1.812287E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.361 | TFLOPs: 23.41 | +63: iteration 71810/ 73814 | consumed samples: 36766720 | consumed tokens: 75298242560 | elapsed time per iteration (s): 2.23 | learning rate: 2.033E-05 | global batch size: 512 | lm loss: 1.801985E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.895 | TFLOPs: 23.67 | +63: iteration 71820/ 73814 | consumed samples: 36771840 | consumed tokens: 75308728320 | elapsed time per iteration (s): 2.23 | learning rate: 2.033E-05 | global batch size: 512 | lm loss: 1.792776E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.077 | TFLOPs: 23.69 | +63: iteration 71830/ 73814 | consumed samples: 36776960 | consumed tokens: 75319214080 | elapsed time per iteration (s): 2.25 | learning rate: 2.033E-05 | global batch size: 512 | lm loss: 1.808903E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.945 | TFLOPs: 23.47 | +63: iteration 71840/ 73814 | consumed samples: 36782080 | consumed tokens: 75329699840 | elapsed time per iteration (s): 2.26 | learning rate: 2.032E-05 | global batch size: 512 | lm loss: 1.810695E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.472 | TFLOPs: 23.31 | +63: iteration 71850/ 73814 | consumed samples: 36787200 | consumed tokens: 75340185600 | elapsed time per iteration (s): 2.24 | learning rate: 2.032E-05 | global batch size: 512 | lm loss: 1.805377E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.055 | TFLOPs: 23.58 | +63: iteration 71860/ 73814 | consumed samples: 36792320 | consumed tokens: 75350671360 | elapsed time per iteration (s): 2.23 | learning rate: 2.032E-05 | global batch size: 512 | lm loss: 1.783495E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.032 | TFLOPs: 23.68 | +63: iteration 71870/ 73814 | consumed samples: 36797440 | consumed tokens: 75361157120 | elapsed time per iteration (s): 2.24 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 1.821098E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.031 | TFLOPs: 23.58 | +63: iteration 71880/ 73814 | consumed samples: 36802560 | consumed tokens: 75371642880 | elapsed time per iteration (s): 2.23 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 1.780357E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.627 | TFLOPs: 23.64 | +63: iteration 71890/ 73814 | consumed samples: 36807680 | consumed tokens: 75382128640 | elapsed time per iteration (s): 2.23 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 1.802575E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.621 | TFLOPs: 23.64 | +63: iteration 71900/ 73814 | consumed samples: 36812800 | consumed tokens: 75392614400 | elapsed time per iteration (s): 2.25 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.809299E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.607 | TFLOPs: 23.43 | +63: iteration 71910/ 73814 | consumed samples: 36817920 | consumed tokens: 75403100160 | elapsed time per iteration (s): 2.23 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.818588E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.016 | TFLOPs: 23.68 | +63: iteration 71920/ 73814 | consumed samples: 36823040 | consumed tokens: 75413585920 | elapsed time per iteration (s): 2.25 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.785601E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.161 | TFLOPs: 23.39 | +63: iteration 71930/ 73814 | consumed samples: 36828160 | consumed tokens: 75424071680 | elapsed time per iteration (s): 2.24 | learning rate: 2.030E-05 | global batch size: 512 | lm loss: 1.814400E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.471 | TFLOPs: 23.52 | +63: iteration 71940/ 73814 | consumed samples: 36833280 | consumed tokens: 75434557440 | elapsed time per iteration (s): 2.23 | learning rate: 2.029E-05 | global batch size: 512 | lm loss: 1.804303E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.367 | TFLOPs: 23.61 | +63: iteration 71950/ 73814 | consumed samples: 36838400 | consumed tokens: 75445043200 | elapsed time per iteration (s): 2.26 | learning rate: 2.029E-05 | global batch size: 512 | lm loss: 1.782760E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.405 | TFLOPs: 23.31 | +63: iteration 71960/ 73814 | consumed samples: 36843520 | consumed tokens: 75455528960 | elapsed time per iteration (s): 2.23 | learning rate: 2.029E-05 | global batch size: 512 | lm loss: 1.786858E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.446 | TFLOPs: 23.62 | +63: iteration 71970/ 73814 | consumed samples: 36848640 | consumed tokens: 75466014720 | elapsed time per iteration (s): 2.23 | learning rate: 2.028E-05 | global batch size: 512 | lm loss: 1.797136E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.876 | TFLOPs: 23.66 | +63: iteration 71980/ 73814 | consumed samples: 36853760 | consumed tokens: 75476500480 | elapsed time per iteration (s): 2.25 | learning rate: 2.028E-05 | global batch size: 512 | lm loss: 1.808811E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.621 | TFLOPs: 23.43 | +63: iteration 71990/ 73814 | consumed samples: 36858880 | consumed tokens: 75486986240 | elapsed time per iteration (s): 2.26 | learning rate: 2.028E-05 | global batch size: 512 | lm loss: 1.800784E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.038 | TFLOPs: 23.37 | + 0: [2022-12-02 12:09:45,597] [INFO] [logging.py:68:log_dist] [Rank 0] step=72000, skipped=0, lr=[2.027365418180334e-05, 2.027365418180334e-05, 2.027365418180334e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: steps: 72000 loss: 1.7776 iter time (s): 2.295 samples/sec: 223.129 +63: iteration 72000/ 73814 | consumed samples: 36864000 | consumed tokens: 75497472000 | elapsed time per iteration (s): 2.25 | learning rate: 2.027E-05 | global batch size: 512 | lm loss: 1.809244E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.002 | TFLOPs: 23.47 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 72000 | lm loss value: 1.782451E+00 | lm loss PPL: 5.944406E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 72010/ 73814 | consumed samples: 36869120 | consumed tokens: 75507957760 | elapsed time per iteration (s): 2.31 | learning rate: 2.027E-05 | global batch size: 512 | lm loss: 1.803395E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.947 | TFLOPs: 22.85 | +63: iteration 72020/ 73814 | consumed samples: 36874240 | consumed tokens: 75518443520 | elapsed time per iteration (s): 2.24 | learning rate: 2.027E-05 | global batch size: 512 | lm loss: 1.796808E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.496 | TFLOPs: 23.52 | +63: iteration 72030/ 73814 | consumed samples: 36879360 | consumed tokens: 75528929280 | elapsed time per iteration (s): 2.25 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.801135E+00 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.527 | TFLOPs: 23.42 | +63: iteration 72040/ 73814 | consumed samples: 36884480 | consumed tokens: 75539415040 | elapsed time per iteration (s): 2.31 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.813727E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.466 | TFLOPs: 22.80 | +63: iteration 72050/ 73814 | consumed samples: 36889600 | consumed tokens: 75549900800 | elapsed time per iteration (s): 2.24 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.787457E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.849 | TFLOPs: 23.56 | +63: iteration 72060/ 73814 | consumed samples: 36894720 | consumed tokens: 75560386560 | elapsed time per iteration (s): 2.24 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 1.810387E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.024 | TFLOPs: 23.58 | +63: iteration 72070/ 73814 | consumed samples: 36899840 | consumed tokens: 75570872320 | elapsed time per iteration (s): 2.26 | learning rate: 2.025E-05 | global batch size: 512 | lm loss: 1.793335E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.080 | TFLOPs: 23.27 | +63: iteration 72080/ 73814 | consumed samples: 36904960 | consumed tokens: 75581358080 | elapsed time per iteration (s): 2.23 | learning rate: 2.025E-05 | global batch size: 512 | lm loss: 1.819892E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.374 | TFLOPs: 23.61 | +63: iteration 72090/ 73814 | consumed samples: 36910080 | consumed tokens: 75591843840 | elapsed time per iteration (s): 2.24 | learning rate: 2.025E-05 | global batch size: 512 | lm loss: 1.806429E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.835 | TFLOPs: 23.56 | +63: iteration 72100/ 73814 | consumed samples: 36915200 | consumed tokens: 75602329600 | elapsed time per iteration (s): 2.25 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.798901E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.119 | TFLOPs: 23.38 | +63: iteration 72110/ 73814 | consumed samples: 36920320 | consumed tokens: 75612815360 | elapsed time per iteration (s): 2.23 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.816231E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.674 | TFLOPs: 23.64 | +63: iteration 72120/ 73814 | consumed samples: 36925440 | consumed tokens: 75623301120 | elapsed time per iteration (s): 2.23 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.801739E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.026 | TFLOPs: 23.68 | +63: iteration 72130/ 73814 | consumed samples: 36930560 | consumed tokens: 75633786880 | elapsed time per iteration (s): 2.23 | learning rate: 2.024E-05 | global batch size: 512 | lm loss: 1.819714E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.104 | TFLOPs: 23.59 | +63: iteration 72140/ 73814 | consumed samples: 36935680 | consumed tokens: 75644272640 | elapsed time per iteration (s): 2.23 | learning rate: 2.023E-05 | global batch size: 512 | lm loss: 1.805029E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.913 | TFLOPs: 23.67 | +63: iteration 72150/ 73814 | consumed samples: 36940800 | consumed tokens: 75654758400 | elapsed time per iteration (s): 2.25 | learning rate: 2.023E-05 | global batch size: 512 | lm loss: 1.781786E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.652 | TFLOPs: 23.44 | +63: iteration 72160/ 73814 | consumed samples: 36945920 | consumed tokens: 75665244160 | elapsed time per iteration (s): 2.23 | learning rate: 2.023E-05 | global batch size: 512 | lm loss: 1.818361E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.106 | TFLOPs: 23.59 | +63: iteration 72170/ 73814 | consumed samples: 36951040 | consumed tokens: 75675729920 | elapsed time per iteration (s): 2.23 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.805317E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.194 | TFLOPs: 23.59 | +63: iteration 72180/ 73814 | consumed samples: 36956160 | consumed tokens: 75686215680 | elapsed time per iteration (s): 2.23 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.813989E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.458 | TFLOPs: 23.62 | +63: iteration 72190/ 73814 | consumed samples: 36961280 | consumed tokens: 75696701440 | elapsed time per iteration (s): 2.25 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.791132E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.752 | TFLOPs: 23.45 | +63: iteration 72200/ 73814 | consumed samples: 36966400 | consumed tokens: 75707187200 | elapsed time per iteration (s): 2.26 | learning rate: 2.022E-05 | global batch size: 512 | lm loss: 1.808361E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.056 | TFLOPs: 23.27 | +63: iteration 72210/ 73814 | consumed samples: 36971520 | consumed tokens: 75717672960 | elapsed time per iteration (s): 2.24 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.779905E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.146 | TFLOPs: 23.49 | +63: iteration 72220/ 73814 | consumed samples: 36976640 | consumed tokens: 75728158720 | elapsed time per iteration (s): 2.24 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.798909E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.218 | TFLOPs: 23.49 | +63: iteration 72230/ 73814 | consumed samples: 36981760 | consumed tokens: 75738644480 | elapsed time per iteration (s): 2.25 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.786736E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.240 | TFLOPs: 23.39 | +63: iteration 72240/ 73814 | consumed samples: 36986880 | consumed tokens: 75749130240 | elapsed time per iteration (s): 2.23 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 1.816559E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.985 | TFLOPs: 23.68 | +63: iteration 72250/ 73814 | consumed samples: 36992000 | consumed tokens: 75759616000 | elapsed time per iteration (s): 2.24 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.808471E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.498 | TFLOPs: 23.52 | +63: iteration 72260/ 73814 | consumed samples: 36997120 | consumed tokens: 75770101760 | elapsed time per iteration (s): 2.23 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.797832E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.045 | TFLOPs: 23.68 | +63: iteration 72270/ 73814 | consumed samples: 37002240 | consumed tokens: 75780587520 | elapsed time per iteration (s): 2.24 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.810009E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.304 | TFLOPs: 23.50 | +63: iteration 72280/ 73814 | consumed samples: 37007360 | consumed tokens: 75791073280 | elapsed time per iteration (s): 2.23 | learning rate: 2.020E-05 | global batch size: 512 | lm loss: 1.802249E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.870 | TFLOPs: 23.66 | +63: iteration 72290/ 73814 | consumed samples: 37012480 | consumed tokens: 75801559040 | elapsed time per iteration (s): 2.24 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.806235E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.172 | TFLOPs: 23.49 | +63: iteration 72300/ 73814 | consumed samples: 37017600 | consumed tokens: 75812044800 | elapsed time per iteration (s): 2.24 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.788585E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.443 | TFLOPs: 23.52 | +63: iteration 72310/ 73814 | consumed samples: 37022720 | consumed tokens: 75822530560 | elapsed time per iteration (s): 2.26 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.786917E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.470 | TFLOPs: 23.31 | +63: iteration 72320/ 73814 | consumed samples: 37027840 | consumed tokens: 75833016320 | elapsed time per iteration (s): 2.23 | learning rate: 2.019E-05 | global batch size: 512 | lm loss: 1.807224E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.959 | TFLOPs: 23.67 | +63: iteration 72330/ 73814 | consumed samples: 37032960 | consumed tokens: 75843502080 | elapsed time per iteration (s): 2.24 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.801546E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.421 | TFLOPs: 23.51 | +63: iteration 72340/ 73814 | consumed samples: 37038080 | consumed tokens: 75853987840 | elapsed time per iteration (s): 2.25 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.790026E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.423 | TFLOPs: 23.41 | +63: iteration 72350/ 73814 | consumed samples: 37043200 | consumed tokens: 75864473600 | elapsed time per iteration (s): 2.25 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.814438E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.667 | TFLOPs: 23.44 | +63: iteration 72360/ 73814 | consumed samples: 37048320 | consumed tokens: 75874959360 | elapsed time per iteration (s): 2.25 | learning rate: 2.018E-05 | global batch size: 512 | lm loss: 1.817371E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.915 | TFLOPs: 23.46 | +63: iteration 72370/ 73814 | consumed samples: 37053440 | consumed tokens: 75885445120 | elapsed time per iteration (s): 2.23 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.814618E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.188 | TFLOPs: 23.59 | +63: iteration 72380/ 73814 | consumed samples: 37058560 | consumed tokens: 75895930880 | elapsed time per iteration (s): 2.27 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.805131E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.365 | TFLOPs: 23.20 | +63: iteration 72390/ 73814 | consumed samples: 37063680 | consumed tokens: 75906416640 | elapsed time per iteration (s): 2.26 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.776514E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.102 | TFLOPs: 23.28 | +63: iteration 72400/ 73814 | consumed samples: 37068800 | consumed tokens: 75916902400 | elapsed time per iteration (s): 2.24 | learning rate: 2.017E-05 | global batch size: 512 | lm loss: 1.798401E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.218 | TFLOPs: 23.49 | +63: iteration 72410/ 73814 | consumed samples: 37073920 | consumed tokens: 75927388160 | elapsed time per iteration (s): 2.23 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.807084E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.893 | TFLOPs: 23.67 | +63: iteration 72420/ 73814 | consumed samples: 37079040 | consumed tokens: 75937873920 | elapsed time per iteration (s): 2.24 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.785875E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.770 | TFLOPs: 23.55 | +63: iteration 72430/ 73814 | consumed samples: 37084160 | consumed tokens: 75948359680 | elapsed time per iteration (s): 2.25 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.815931E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.025 | TFLOPs: 23.47 | +63: iteration 72440/ 73814 | consumed samples: 37089280 | consumed tokens: 75958845440 | elapsed time per iteration (s): 2.24 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 1.817339E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.454 | TFLOPs: 23.52 | +63: iteration 72450/ 73814 | consumed samples: 37094400 | consumed tokens: 75969331200 | elapsed time per iteration (s): 2.23 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.805884E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.421 | TFLOPs: 23.62 | +63: iteration 72460/ 73814 | consumed samples: 37099520 | consumed tokens: 75979816960 | elapsed time per iteration (s): 2.23 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.812212E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.871 | TFLOPs: 23.66 | +63: iteration 72470/ 73814 | consumed samples: 37104640 | consumed tokens: 75990302720 | elapsed time per iteration (s): 2.25 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.795799E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.738 | TFLOPs: 23.44 | +63: iteration 72480/ 73814 | consumed samples: 37109760 | consumed tokens: 76000788480 | elapsed time per iteration (s): 2.23 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.787717E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.807 | TFLOPs: 23.66 | +63: iteration 72490/ 73814 | consumed samples: 37114880 | consumed tokens: 76011274240 | elapsed time per iteration (s): 2.24 | learning rate: 2.015E-05 | global batch size: 512 | lm loss: 1.788358E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.248 | TFLOPs: 23.50 | +63: iteration 72500/ 73814 | consumed samples: 37120000 | consumed tokens: 76021760000 | elapsed time per iteration (s): 2.23 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.814160E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.255 | TFLOPs: 23.60 | +63: iteration 72510/ 73814 | consumed samples: 37125120 | consumed tokens: 76032245760 | elapsed time per iteration (s): 2.26 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.797304E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.179 | TFLOPs: 23.28 | +63: iteration 72520/ 73814 | consumed samples: 37130240 | consumed tokens: 76042731520 | elapsed time per iteration (s): 2.24 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.807116E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.019 | TFLOPs: 23.58 | +63: iteration 72530/ 73814 | consumed samples: 37135360 | consumed tokens: 76053217280 | elapsed time per iteration (s): 2.24 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.785802E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.279 | TFLOPs: 23.50 | +63: iteration 72540/ 73814 | consumed samples: 37140480 | consumed tokens: 76063703040 | elapsed time per iteration (s): 2.24 | learning rate: 2.014E-05 | global batch size: 512 | lm loss: 1.812299E+00 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.378 | TFLOPs: 23.51 | +63: iteration 72550/ 73814 | consumed samples: 37145600 | consumed tokens: 76074188800 | elapsed time per iteration (s): 2.23 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.831851E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.837 | TFLOPs: 23.66 | +63: iteration 72560/ 73814 | consumed samples: 37150720 | consumed tokens: 76084674560 | elapsed time per iteration (s): 2.24 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.797277E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.284 | TFLOPs: 23.50 | +63: iteration 72570/ 73814 | consumed samples: 37155840 | consumed tokens: 76095160320 | elapsed time per iteration (s): 2.24 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.818480E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.974 | TFLOPs: 23.57 | +63: iteration 72580/ 73814 | consumed samples: 37160960 | consumed tokens: 76105646080 | elapsed time per iteration (s): 2.24 | learning rate: 2.013E-05 | global batch size: 512 | lm loss: 1.821402E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.086 | TFLOPs: 23.48 | +63: iteration 72590/ 73814 | consumed samples: 37166080 | consumed tokens: 76116131840 | elapsed time per iteration (s): 2.24 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.791850E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.144 | TFLOPs: 23.49 | +63: iteration 72600/ 73814 | consumed samples: 37171200 | consumed tokens: 76126617600 | elapsed time per iteration (s): 2.24 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.798454E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.390 | TFLOPs: 23.51 | +63: iteration 72610/ 73814 | consumed samples: 37176320 | consumed tokens: 76137103360 | elapsed time per iteration (s): 2.24 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.803192E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.902 | TFLOPs: 23.56 | +63: iteration 72620/ 73814 | consumed samples: 37181440 | consumed tokens: 76147589120 | elapsed time per iteration (s): 2.23 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.826547E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.472 | TFLOPs: 23.62 | +63: iteration 72630/ 73814 | consumed samples: 37186560 | consumed tokens: 76158074880 | elapsed time per iteration (s): 2.23 | learning rate: 2.012E-05 | global batch size: 512 | lm loss: 1.805569E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.666 | TFLOPs: 23.64 | +63: iteration 72640/ 73814 | consumed samples: 37191680 | consumed tokens: 76168560640 | elapsed time per iteration (s): 2.24 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.828449E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.390 | TFLOPs: 23.51 | +63: iteration 72650/ 73814 | consumed samples: 37196800 | consumed tokens: 76179046400 | elapsed time per iteration (s): 2.24 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.817095E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.550 | TFLOPs: 23.53 | +63: iteration 72660/ 73814 | consumed samples: 37201920 | consumed tokens: 76189532160 | elapsed time per iteration (s): 2.25 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.803095E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.685 | TFLOPs: 23.44 | +63: iteration 72670/ 73814 | consumed samples: 37207040 | consumed tokens: 76200017920 | elapsed time per iteration (s): 2.23 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.817879E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.305 | TFLOPs: 23.61 | +63: iteration 72680/ 73814 | consumed samples: 37212160 | consumed tokens: 76210503680 | elapsed time per iteration (s): 2.23 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.829564E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.007 | TFLOPs: 23.68 | +63: iteration 72690/ 73814 | consumed samples: 37217280 | consumed tokens: 76220989440 | elapsed time per iteration (s): 2.23 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 1.793416E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.713 | TFLOPs: 23.65 | +63: iteration 72700/ 73814 | consumed samples: 37222400 | consumed tokens: 76231475200 | elapsed time per iteration (s): 2.23 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.813133E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.800 | TFLOPs: 23.66 | +63: iteration 72710/ 73814 | consumed samples: 37227520 | consumed tokens: 76241960960 | elapsed time per iteration (s): 2.23 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.795736E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.874 | TFLOPs: 23.66 | +63: iteration 72720/ 73814 | consumed samples: 37232640 | consumed tokens: 76252446720 | elapsed time per iteration (s): 2.22 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.794719E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.193 | TFLOPs: 23.70 | +63: iteration 72730/ 73814 | consumed samples: 37237760 | consumed tokens: 76262932480 | elapsed time per iteration (s): 2.26 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.814022E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.001 | TFLOPs: 23.37 | +63: iteration 72740/ 73814 | consumed samples: 37242880 | consumed tokens: 76273418240 | elapsed time per iteration (s): 2.24 | learning rate: 2.010E-05 | global batch size: 512 | lm loss: 1.797271E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.203 | TFLOPs: 23.49 | +63: iteration 72750/ 73814 | consumed samples: 37248000 | consumed tokens: 76283904000 | elapsed time per iteration (s): 2.23 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.803057E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.942 | TFLOPs: 23.67 | +63: iteration 72760/ 73814 | consumed samples: 37253120 | consumed tokens: 76294389760 | elapsed time per iteration (s): 2.24 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.810697E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.349 | TFLOPs: 23.51 | +63: iteration 72770/ 73814 | consumed samples: 37258240 | consumed tokens: 76304875520 | elapsed time per iteration (s): 2.23 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.800849E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 72780/ 73814 | consumed samples: 37263360 | consumed tokens: 76315361280 | elapsed time per iteration (s): 2.25 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.798060E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.005 | TFLOPs: 23.47 | +63: iteration 72790/ 73814 | consumed samples: 37268480 | consumed tokens: 76325847040 | elapsed time per iteration (s): 2.24 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.816981E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.073 | TFLOPs: 23.48 | +63: iteration 72800/ 73814 | consumed samples: 37273600 | consumed tokens: 76336332800 | elapsed time per iteration (s): 2.24 | learning rate: 2.009E-05 | global batch size: 512 | lm loss: 1.822511E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.596 | TFLOPs: 23.53 | +63: iteration 72810/ 73814 | consumed samples: 37278720 | consumed tokens: 76346818560 | elapsed time per iteration (s): 2.23 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.825867E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.947 | TFLOPs: 23.67 | +63: iteration 72820/ 73814 | consumed samples: 37283840 | consumed tokens: 76357304320 | elapsed time per iteration (s): 2.24 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.807413E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.838 | TFLOPs: 23.56 | +63: iteration 72830/ 73814 | consumed samples: 37288960 | consumed tokens: 76367790080 | elapsed time per iteration (s): 2.26 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.791537E+00 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.611 | TFLOPs: 23.33 | +63: iteration 72840/ 73814 | consumed samples: 37294080 | consumed tokens: 76378275840 | elapsed time per iteration (s): 2.23 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.817628E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.470 | TFLOPs: 23.62 | +63: iteration 72850/ 73814 | consumed samples: 37299200 | consumed tokens: 76388761600 | elapsed time per iteration (s): 2.26 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.822368E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.259 | TFLOPs: 23.29 | +63: iteration 72860/ 73814 | consumed samples: 37304320 | consumed tokens: 76399247360 | elapsed time per iteration (s): 2.28 | learning rate: 2.008E-05 | global batch size: 512 | lm loss: 1.808116E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.647 | TFLOPs: 23.13 | +63: iteration 72870/ 73814 | consumed samples: 37309440 | consumed tokens: 76409733120 | elapsed time per iteration (s): 2.24 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.781942E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.245 | TFLOPs: 23.50 | +63: iteration 72880/ 73814 | consumed samples: 37314560 | consumed tokens: 76420218880 | elapsed time per iteration (s): 2.23 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.782380E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.804 | TFLOPs: 23.66 | +63: iteration 72890/ 73814 | consumed samples: 37319680 | consumed tokens: 76430704640 | elapsed time per iteration (s): 2.24 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.800942E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.691 | TFLOPs: 23.54 | +63: iteration 72900/ 73814 | consumed samples: 37324800 | consumed tokens: 76441190400 | elapsed time per iteration (s): 2.26 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.799415E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.874 | TFLOPs: 23.36 | +63: iteration 72910/ 73814 | consumed samples: 37329920 | consumed tokens: 76451676160 | elapsed time per iteration (s): 2.24 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.810008E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.431 | TFLOPs: 23.52 | +63: iteration 72920/ 73814 | consumed samples: 37335040 | consumed tokens: 76462161920 | elapsed time per iteration (s): 2.24 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.807642E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.337 | TFLOPs: 23.51 | +63: iteration 72930/ 73814 | consumed samples: 37340160 | consumed tokens: 76472647680 | elapsed time per iteration (s): 2.23 | learning rate: 2.007E-05 | global batch size: 512 | lm loss: 1.788159E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.892 | TFLOPs: 23.67 | +63: iteration 72940/ 73814 | consumed samples: 37345280 | consumed tokens: 76483133440 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.806764E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.148 | TFLOPs: 23.59 | +63: iteration 72950/ 73814 | consumed samples: 37350400 | consumed tokens: 76493619200 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.820635E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.242 | TFLOPs: 23.60 | +63: iteration 72960/ 73814 | consumed samples: 37355520 | consumed tokens: 76504104960 | elapsed time per iteration (s): 2.25 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.796564E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.625 | TFLOPs: 23.43 | +63: iteration 72970/ 73814 | consumed samples: 37360640 | consumed tokens: 76514590720 | elapsed time per iteration (s): 2.25 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.790793E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.523 | TFLOPs: 23.42 | +63: iteration 72980/ 73814 | consumed samples: 37365760 | consumed tokens: 76525076480 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.785795E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.903 | TFLOPs: 23.67 | +63: iteration 72990/ 73814 | consumed samples: 37370880 | consumed tokens: 76535562240 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.820341E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.001 | TFLOPs: 23.68 | +63: iteration 73000/ 73814 | consumed samples: 37376000 | consumed tokens: 76546048000 | elapsed time per iteration (s): 2.23 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 1.804525E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.393 | TFLOPs: 23.61 | +63: ------------------------------------------------------------------------------------------- +63: valid loss at iteration 73000 | lm loss value: 1.844314E+00 | lm loss PPL: 6.323763E+00 | +63: ------------------------------------------------------------------------------------------- +63: iteration 73010/ 73814 | consumed samples: 37381120 | consumed tokens: 76556533760 | elapsed time per iteration (s): 2.28 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.794631E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.299 | TFLOPs: 23.09 | +63: iteration 73020/ 73814 | consumed samples: 37386240 | consumed tokens: 76567019520 | elapsed time per iteration (s): 2.23 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.801573E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.992 | TFLOPs: 23.68 | +63: iteration 73030/ 73814 | consumed samples: 37391360 | consumed tokens: 76577505280 | elapsed time per iteration (s): 2.23 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.807745E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.931 | TFLOPs: 23.67 | +63: iteration 73040/ 73814 | consumed samples: 37396480 | consumed tokens: 76587991040 | elapsed time per iteration (s): 2.23 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.800221E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.927 | TFLOPs: 23.67 | +63: iteration 73050/ 73814 | consumed samples: 37401600 | consumed tokens: 76598476800 | elapsed time per iteration (s): 2.25 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.802530E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.717 | TFLOPs: 23.44 | +63: iteration 73060/ 73814 | consumed samples: 37406720 | consumed tokens: 76608962560 | elapsed time per iteration (s): 2.25 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.808678E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.908 | TFLOPs: 23.46 | +63: iteration 73070/ 73814 | consumed samples: 37411840 | consumed tokens: 76619448320 | elapsed time per iteration (s): 2.22 | learning rate: 2.005E-05 | global batch size: 512 | lm loss: 1.797323E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.190 | TFLOPs: 23.70 | +63: iteration 73080/ 73814 | consumed samples: 37416960 | consumed tokens: 76629934080 | elapsed time per iteration (s): 2.23 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.801735E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.249 | TFLOPs: 23.60 | +63: iteration 73090/ 73814 | consumed samples: 37422080 | consumed tokens: 76640419840 | elapsed time per iteration (s): 2.31 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.803003E+00 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 221.889 | TFLOPs: 22.84 | +63: iteration 73100/ 73814 | consumed samples: 37427200 | consumed tokens: 76650905600 | elapsed time per iteration (s): 2.23 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.798911E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.795 | TFLOPs: 23.66 | +63: iteration 73110/ 73814 | consumed samples: 37432320 | consumed tokens: 76661391360 | elapsed time per iteration (s): 2.28 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.808730E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.088 | TFLOPs: 23.07 | +63: iteration 73120/ 73814 | consumed samples: 37437440 | consumed tokens: 76671877120 | elapsed time per iteration (s): 2.28 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.791462E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.405 | TFLOPs: 23.10 | +63: iteration 73130/ 73814 | consumed samples: 37442560 | consumed tokens: 76682362880 | elapsed time per iteration (s): 2.27 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.798845E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.829 | TFLOPs: 23.25 | +63: iteration 73140/ 73814 | consumed samples: 37447680 | consumed tokens: 76692848640 | elapsed time per iteration (s): 2.25 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.801416E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.504 | TFLOPs: 23.42 | +63: iteration 73150/ 73814 | consumed samples: 37452800 | consumed tokens: 76703334400 | elapsed time per iteration (s): 2.23 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.811690E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.986 | TFLOPs: 23.68 | +63: iteration 73160/ 73814 | consumed samples: 37457920 | consumed tokens: 76713820160 | elapsed time per iteration (s): 2.27 | learning rate: 2.004E-05 | global batch size: 512 | lm loss: 1.808979E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.683 | TFLOPs: 23.23 | +63: iteration 73170/ 73814 | consumed samples: 37463040 | consumed tokens: 76724305920 | elapsed time per iteration (s): 2.23 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.792369E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.038 | TFLOPs: 23.68 | +63: iteration 73180/ 73814 | consumed samples: 37468160 | consumed tokens: 76734791680 | elapsed time per iteration (s): 2.23 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.787569E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.350 | TFLOPs: 23.61 | +63: iteration 73190/ 73814 | consumed samples: 37473280 | consumed tokens: 76745277440 | elapsed time per iteration (s): 2.25 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.817774E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.058 | TFLOPs: 23.48 | +63: iteration 73200/ 73814 | consumed samples: 37478400 | consumed tokens: 76755763200 | elapsed time per iteration (s): 2.33 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.809685E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 219.786 | TFLOPs: 22.63 | +63: iteration 73210/ 73814 | consumed samples: 37483520 | consumed tokens: 76766248960 | elapsed time per iteration (s): 2.32 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.798161E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 220.877 | TFLOPs: 22.74 | +63: iteration 73220/ 73814 | consumed samples: 37488640 | consumed tokens: 76776734720 | elapsed time per iteration (s): 2.24 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.804151E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.920 | TFLOPs: 23.57 | +63: iteration 73230/ 73814 | consumed samples: 37493760 | consumed tokens: 76787220480 | elapsed time per iteration (s): 2.27 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.805119E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.358 | TFLOPs: 23.20 | +63: iteration 73240/ 73814 | consumed samples: 37498880 | consumed tokens: 76797706240 | elapsed time per iteration (s): 2.34 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.784381E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.358 | TFLOPs: 22.48 | +63: iteration 73250/ 73814 | consumed samples: 37504000 | consumed tokens: 76808192000 | elapsed time per iteration (s): 2.25 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.789309E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.849 | TFLOPs: 23.46 | +63: iteration 73260/ 73814 | consumed samples: 37509120 | consumed tokens: 76818677760 | elapsed time per iteration (s): 2.47 | learning rate: 2.003E-05 | global batch size: 512 | lm loss: 1.819493E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 207.420 | TFLOPs: 21.35 | +63: iteration 73270/ 73814 | consumed samples: 37514240 | consumed tokens: 76829163520 | elapsed time per iteration (s): 2.24 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.802046E+00 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.785 | TFLOPs: 23.55 | +63: iteration 73280/ 73814 | consumed samples: 37519360 | consumed tokens: 76839649280 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.805078E+00 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.279 | TFLOPs: 23.60 | +63: iteration 73290/ 73814 | consumed samples: 37524480 | consumed tokens: 76850135040 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.816614E+00 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.024 | TFLOPs: 23.68 | +63: iteration 73300/ 73814 | consumed samples: 37529600 | consumed tokens: 76860620800 | elapsed time per iteration (s): 2.24 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.788108E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.915 | TFLOPs: 23.57 | +63: iteration 73310/ 73814 | consumed samples: 37534720 | consumed tokens: 76871106560 | elapsed time per iteration (s): 2.25 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.783189E+00 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.691 | TFLOPs: 23.44 | +63: iteration 73320/ 73814 | consumed samples: 37539840 | consumed tokens: 76881592320 | elapsed time per iteration (s): 2.30 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.788905E+00 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 222.867 | TFLOPs: 22.94 | +63: iteration 73330/ 73814 | consumed samples: 37544960 | consumed tokens: 76892078080 | elapsed time per iteration (s): 2.25 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.803963E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.866 | TFLOPs: 23.46 | +63: iteration 73340/ 73814 | consumed samples: 37550080 | consumed tokens: 76902563840 | elapsed time per iteration (s): 2.23 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.817529E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.826 | TFLOPs: 23.66 | +63: iteration 73350/ 73814 | consumed samples: 37555200 | consumed tokens: 76913049600 | elapsed time per iteration (s): 2.25 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.811982E+00 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.049 | TFLOPs: 23.48 | +63: iteration 73360/ 73814 | consumed samples: 37560320 | consumed tokens: 76923535360 | elapsed time per iteration (s): 2.25 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.807583E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.122 | TFLOPs: 23.38 | +63: iteration 73370/ 73814 | consumed samples: 37565440 | consumed tokens: 76934021120 | elapsed time per iteration (s): 2.24 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.811410E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.714 | TFLOPs: 23.55 | +63: iteration 73380/ 73814 | consumed samples: 37570560 | consumed tokens: 76944506880 | elapsed time per iteration (s): 2.25 | learning rate: 2.002E-05 | global batch size: 512 | lm loss: 1.799724E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.982 | TFLOPs: 23.47 | +63: iteration 73390/ 73814 | consumed samples: 37575680 | consumed tokens: 76954992640 | elapsed time per iteration (s): 2.29 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.796807E+00 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 223.756 | TFLOPs: 23.03 | +63: iteration 73400/ 73814 | consumed samples: 37580800 | consumed tokens: 76965478400 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.825207E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.189 | TFLOPs: 23.49 | +63: iteration 73410/ 73814 | consumed samples: 37585920 | consumed tokens: 76975964160 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.815041E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.859 | TFLOPs: 23.56 | +63: iteration 73420/ 73814 | consumed samples: 37591040 | consumed tokens: 76986449920 | elapsed time per iteration (s): 2.39 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.806438E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 214.411 | TFLOPs: 22.07 | +63: iteration 73430/ 73814 | consumed samples: 37596160 | consumed tokens: 76996935680 | elapsed time per iteration (s): 2.35 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.792082E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 217.541 | TFLOPs: 22.39 | +63: iteration 73440/ 73814 | consumed samples: 37601280 | consumed tokens: 77007421440 | elapsed time per iteration (s): 2.36 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.810974E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 216.760 | TFLOPs: 22.31 | +63: iteration 73450/ 73814 | consumed samples: 37606400 | consumed tokens: 77017907200 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.782982E+00 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.676 | TFLOPs: 23.44 | +63: iteration 73460/ 73814 | consumed samples: 37611520 | consumed tokens: 77028392960 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.809269E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.249 | TFLOPs: 23.39 | +63: iteration 73470/ 73814 | consumed samples: 37616640 | consumed tokens: 77038878720 | elapsed time per iteration (s): 2.23 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.799007E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.549 | TFLOPs: 23.63 | +63: iteration 73480/ 73814 | consumed samples: 37621760 | consumed tokens: 77049364480 | elapsed time per iteration (s): 2.26 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.800952E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.708 | TFLOPs: 23.34 | +63: iteration 73490/ 73814 | consumed samples: 37626880 | consumed tokens: 77059850240 | elapsed time per iteration (s): 2.28 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.784289E+00 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.510 | TFLOPs: 23.11 | +63: iteration 73500/ 73814 | consumed samples: 37632000 | consumed tokens: 77070336000 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.809549E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.702 | TFLOPs: 23.44 | +63: iteration 73510/ 73814 | consumed samples: 37637120 | consumed tokens: 77080821760 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.790188E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.568 | TFLOPs: 23.53 | +63: iteration 73520/ 73814 | consumed samples: 37642240 | consumed tokens: 77091307520 | elapsed time per iteration (s): 2.28 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.792813E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.658 | TFLOPs: 23.13 | +63: iteration 73530/ 73814 | consumed samples: 37647360 | consumed tokens: 77101793280 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.800170E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.733 | TFLOPs: 23.44 | +63: iteration 73540/ 73814 | consumed samples: 37652480 | consumed tokens: 77112279040 | elapsed time per iteration (s): 2.25 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.791322E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.300 | TFLOPs: 23.40 | +63: iteration 73550/ 73814 | consumed samples: 37657600 | consumed tokens: 77122764800 | elapsed time per iteration (s): 2.24 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.803194E+00 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.320 | TFLOPs: 23.50 | +63: iteration 73560/ 73814 | consumed samples: 37662720 | consumed tokens: 77133250560 | elapsed time per iteration (s): 2.34 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 1.792167E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 218.560 | TFLOPs: 22.50 | +63: iteration 73570/ 73814 | consumed samples: 37667840 | consumed tokens: 77143736320 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.797102E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.956 | TFLOPs: 23.57 | +63: iteration 73580/ 73814 | consumed samples: 37672960 | consumed tokens: 77154222080 | elapsed time per iteration (s): 2.27 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.803050E+00 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 225.779 | TFLOPs: 23.24 | +63: iteration 73590/ 73814 | consumed samples: 37678080 | consumed tokens: 77164707840 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.794441E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.215 | TFLOPs: 23.60 | +63: iteration 73600/ 73814 | consumed samples: 37683200 | consumed tokens: 77175193600 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.800702E+00 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.182 | TFLOPs: 23.39 | +63: iteration 73610/ 73814 | consumed samples: 37688320 | consumed tokens: 77185679360 | elapsed time per iteration (s): 2.67 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.784182E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 191.857 | TFLOPs: 19.75 | +63: iteration 73620/ 73814 | consumed samples: 37693440 | consumed tokens: 77196165120 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.803890E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.199 | TFLOPs: 23.59 | +63: iteration 73630/ 73814 | consumed samples: 37698560 | consumed tokens: 77206650880 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.806753E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.477 | TFLOPs: 23.62 | +63: iteration 73640/ 73814 | consumed samples: 37703680 | consumed tokens: 77217136640 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.810606E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.898 | TFLOPs: 23.67 | +63: iteration 73650/ 73814 | consumed samples: 37708800 | consumed tokens: 77227622400 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.809193E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.288 | TFLOPs: 23.50 | +63: iteration 73660/ 73814 | consumed samples: 37713920 | consumed tokens: 77238108160 | elapsed time per iteration (s): 2.26 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.803358E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 226.520 | TFLOPs: 23.32 | +63: iteration 73670/ 73814 | consumed samples: 37719040 | consumed tokens: 77248593920 | elapsed time per iteration (s): 2.28 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.778393E+00 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.917 | TFLOPs: 23.15 | +63: iteration 73680/ 73814 | consumed samples: 37724160 | consumed tokens: 77259079680 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.823247E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 228.390 | TFLOPs: 23.51 | +63: iteration 73690/ 73814 | consumed samples: 37729280 | consumed tokens: 77269565440 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.816088E+00 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 230.023 | TFLOPs: 23.68 | +63: iteration 73700/ 73814 | consumed samples: 37734400 | consumed tokens: 77280051200 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.824075E+00 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.922 | TFLOPs: 23.67 | +63: iteration 73710/ 73814 | consumed samples: 37739520 | consumed tokens: 77290536960 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.812996E+00 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.957 | TFLOPs: 23.47 | +63: iteration 73720/ 73814 | consumed samples: 37744640 | consumed tokens: 77301022720 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.828611E+00 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.451 | TFLOPs: 23.41 | +63: iteration 73730/ 73814 | consumed samples: 37749760 | consumed tokens: 77311508480 | elapsed time per iteration (s): 2.54 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.803869E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 201.492 | TFLOPs: 20.74 | +63: iteration 73740/ 73814 | consumed samples: 37754880 | consumed tokens: 77321994240 | elapsed time per iteration (s): 2.28 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.799333E+00 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 224.205 | TFLOPs: 23.08 | +63: iteration 73750/ 73814 | consumed samples: 37760000 | consumed tokens: 77332480000 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.800757E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.837 | TFLOPs: 23.66 | +63: iteration 73760/ 73814 | consumed samples: 37765120 | consumed tokens: 77342965760 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.810507E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.898 | TFLOPs: 23.46 | +63: iteration 73770/ 73814 | consumed samples: 37770240 | consumed tokens: 77353451520 | elapsed time per iteration (s): 2.23 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.787811E+00 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.863 | TFLOPs: 23.66 | +63: iteration 73780/ 73814 | consumed samples: 37775360 | consumed tokens: 77363937280 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.789015E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.546 | TFLOPs: 23.42 | +63: iteration 73790/ 73814 | consumed samples: 37780480 | consumed tokens: 77374423040 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.813247E+00 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.829 | TFLOPs: 23.45 | +63: iteration 73800/ 73814 | consumed samples: 37785600 | consumed tokens: 77384908800 | elapsed time per iteration (s): 2.25 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.805023E+00 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.438 | TFLOPs: 23.41 | +63: iteration 73810/ 73814 | consumed samples: 37790720 | consumed tokens: 77395394560 | elapsed time per iteration (s): 2.24 | learning rate: 2.000E-05 | global batch size: 512 | lm loss: 1.805443E+00 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 229.024 | TFLOPs: 23.58 | + 0: [after training is done] datetime: 2022-12-02 13:17:53 + 0: saving checkpoint at iteration 73814 to checkpoints_3b977b +63: ------------------------------------------------------------------------------------------------------------ +63: valid loss at the end of training for val data | lm loss value: 1.756912E+00 | lm loss PPL: 5.794519E+00 | +63: ------------------------------------------------------------------------------------------------------------ + 0: [2022-12-02 13:17:54,020] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step73814 is begin to save! +32: [2022-12-02 13:17:54,793] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_21-model_00-model_states.pt... + 0: [2022-12-02 13:17:54,851] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_01-model_00-model_states.pt... +32: [2022-12-02 13:17:55,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_21-model_00-model_states.pt. +32: [2022-12-02 13:17:55,254] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_22-model_00-model_states.pt... + 0: [2022-12-02 13:17:55,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_01-model_00-model_states.pt. + 0: [2022-12-02 13:17:55,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_03-model_00-model_states.pt... +32: [2022-12-02 13:17:55,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_22-model_00-model_states.pt. +32: [2022-12-02 13:17:55,492] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_23-model_00-model_states.pt... + 0: [2022-12-02 13:17:55,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_03-model_00-model_states.pt. + 0: [2022-12-02 13:17:55,630] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_04-model_00-model_states.pt... +32: [2022-12-02 13:17:55,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_23-model_00-model_states.pt. +32: [2022-12-02 13:17:55,725] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_24-model_00-model_states.pt... + 0: [2022-12-02 13:17:55,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_04-model_00-model_states.pt. + 0: [2022-12-02 13:17:55,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_05-model_00-model_states.pt... +32: [2022-12-02 13:17:55,957] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_24-model_00-model_states.pt. +32: [2022-12-02 13:17:55,958] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_25-model_00-model_states.pt... + 0: [2022-12-02 13:17:56,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_05-model_00-model_states.pt. + 0: [2022-12-02 13:17:56,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_06-model_00-model_states.pt... +32: [2022-12-02 13:17:56,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_25-model_00-model_states.pt. +32: [2022-12-02 13:17:56,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_26-model_00-model_states.pt... +32: [2022-12-02 13:17:56,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_26-model_00-model_states.pt. +32: [2022-12-02 13:17:56,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_27-model_00-model_states.pt... + 0: [2022-12-02 13:17:56,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_06-model_00-model_states.pt. + 0: [2022-12-02 13:17:56,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_07-model_00-model_states.pt... +32: [2022-12-02 13:17:56,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_27-model_00-model_states.pt. +32: [2022-12-02 13:17:56,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_28-model_00-model_states.pt... + 0: [2022-12-02 13:17:56,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_07-model_00-model_states.pt. + 0: [2022-12-02 13:17:56,715] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_08-model_00-model_states.pt... +32: [2022-12-02 13:17:56,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_28-model_00-model_states.pt. +32: [2022-12-02 13:17:56,908] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_29-model_00-model_states.pt... + 0: [2022-12-02 13:17:56,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_08-model_00-model_states.pt. + 0: [2022-12-02 13:17:56,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_09-model_00-model_states.pt... +32: [2022-12-02 13:17:57,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_29-model_00-model_states.pt. +32: [2022-12-02 13:17:57,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_30-model_00-model_states.pt... + 0: [2022-12-02 13:17:57,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_09-model_00-model_states.pt. + 0: [2022-12-02 13:17:57,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_10-model_00-model_states.pt... +32: [2022-12-02 13:17:57,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_30-model_00-model_states.pt. +32: [2022-12-02 13:17:57,392] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_31-model_00-model_states.pt... + 0: [2022-12-02 13:17:57,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_10-model_00-model_states.pt. + 0: [2022-12-02 13:17:57,449] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_11-model_00-model_states.pt... +32: [2022-12-02 13:17:57,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_31-model_00-model_states.pt. +32: [2022-12-02 13:17:57,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_32-model_00-model_states.pt... + 0: [2022-12-02 13:17:57,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_11-model_00-model_states.pt. + 0: [2022-12-02 13:17:57,713] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_12-model_00-model_states.pt... +32: [2022-12-02 13:17:57,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_32-model_00-model_states.pt. +32: [2022-12-02 13:17:57,873] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_33-model_00-model_states.pt... + 0: [2022-12-02 13:17:57,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_12-model_00-model_states.pt. + 0: [2022-12-02 13:17:57,956] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_13-model_00-model_states.pt... +32: [2022-12-02 13:17:58,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_33-model_00-model_states.pt. +32: [2022-12-02 13:17:58,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_34-model_00-model_states.pt... + 0: [2022-12-02 13:17:58,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_13-model_00-model_states.pt. + 0: [2022-12-02 13:17:58,192] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_14-model_00-model_states.pt... +32: [2022-12-02 13:17:58,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_34-model_00-model_states.pt. +32: [2022-12-02 13:17:58,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_35-model_00-model_states.pt... + 0: [2022-12-02 13:17:58,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_14-model_00-model_states.pt. + 0: [2022-12-02 13:17:58,430] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_15-model_00-model_states.pt... +32: [2022-12-02 13:17:58,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_35-model_00-model_states.pt. +32: [2022-12-02 13:17:58,595] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_36-model_00-model_states.pt... + 0: [2022-12-02 13:17:58,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_15-model_00-model_states.pt. + 0: [2022-12-02 13:17:58,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_16-model_00-model_states.pt... +32: [2022-12-02 13:17:58,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_36-model_00-model_states.pt. +32: [2022-12-02 13:17:58,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_37-model_00-model_states.pt... + 0: [2022-12-02 13:17:58,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_16-model_00-model_states.pt. + 0: [2022-12-02 13:17:58,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_17-model_00-model_states.pt... +32: [2022-12-02 13:17:59,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_37-model_00-model_states.pt. +32: [2022-12-02 13:17:59,078] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_38-model_00-model_states.pt... + 0: [2022-12-02 13:17:59,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_17-model_00-model_states.pt. + 0: [2022-12-02 13:17:59,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_18-model_00-model_states.pt... +32: [2022-12-02 13:17:59,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_38-model_00-model_states.pt. +32: [2022-12-02 13:17:59,315] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_40-model_00-model_states.pt... +32: [2022-12-02 13:17:59,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_40-model_00-model_states.pt. +32: [2022-12-02 13:17:59,323] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/mp_rank_01_model_states.pt... +32: [2022-12-02 13:17:59,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/mp_rank_01_model_states.pt. + 0: [2022-12-02 13:17:59,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_18-model_00-model_states.pt. + 0: [2022-12-02 13:17:59,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_19-model_00-model_states.pt... + 0: [2022-12-02 13:17:59,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_19-model_00-model_states.pt. + 0: [2022-12-02 13:17:59,638] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/layer_20-model_00-model_states.pt... + 0: [2022-12-02 13:17:59,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/layer_20-model_00-model_states.pt. + 0: [2022-12-02 13:17:59,869] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_3b977b/global_step73814/mp_rank_00_model_states.pt + 0: [2022-12-02 13:17:59,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/mp_rank_00_model_states.pt... + 0: [2022-12-02 13:17:59,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/mp_rank_00_model_states.pt. +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 0: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt... +62: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt... +60: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt... +38: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt... +51: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt... +61: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt... +19: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt... + 4: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +30: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +29: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +49: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt... +53: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt... +56: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt... + 2: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +46: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +20: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +21: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +39: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt... +42: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt... +34: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +50: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt... +12: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt... +35: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt... +58: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt... +54: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... + 6: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt... +40: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt... +63: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt... +59: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 9: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +23: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt... +44: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt... +28: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt... +14: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 8: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 5: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +11: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt... +43: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt... +41: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +31: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt... +13: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt... + 1: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +57: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt... +55: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt... +25: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt... +36: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +37: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt... +27: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt... +33: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt... +52: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt... +48: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt... +45: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt... +47: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt... +17: [2022-12-02 13:18:00,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +32: [2022-12-02 13:18:00,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_0_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:18:00,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:18:00,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_5_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:18:00,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_7_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_1_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_4_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_6_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:18:00,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:18:00,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_2_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +32: [2022-12-02 13:18:00,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt. +32: [2022-12-02 13:18:00,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_3_mp_rank_01_optim_states.pt +32: [2022-12-02 13:18:00,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt. + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_254_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_248_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_253_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_250_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_251_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_255_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:18:00,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:18:00,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:18:00,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +41: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_73_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_78_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_79_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_72_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:18:00,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_225_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_229_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_76_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_121_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_127_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_126_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_125_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_124_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_184_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_191_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_187_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_186_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_190_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_198_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_194_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_196_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_197_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_195_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_58_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_56_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_57_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_61_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_60_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_62_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_222_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_217_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_216_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_220_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_85_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_87_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_82_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_80_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_209_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_45_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_40_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_42_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_46_mp_rank_01_optim_states.pt + 0: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_47_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_43_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-02 13:18:00,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt. + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +53: [2022-12-02 13:18:00,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_168_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_174_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_169_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_173_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_175_mp_rank_01_optim_states.pt + 9: [2022-12-02 13:18:00,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:18:00,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +53: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_224_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 0: [2022-12-02 13:18:00,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_236_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_235_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_234_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_239_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_232_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:18:00,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_135_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_130_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_133_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_129_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_128_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_95_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_93_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_91_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_90_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_92_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_88_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_55_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_50_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_53_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_54_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_51_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_48_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt. + 2: [2022-12-02 13:18:00,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_105_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_109_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_104_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_107_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_106_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt. +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_207_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_204_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_200_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_201_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_206_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_203_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_202_mp_rank_01_optim_states.pt +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:18:00,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:18:00,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_8_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_15_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_11_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_14_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_12_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt. +12: [2022-12-02 13:18:00,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_242_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_247_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_240_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_245_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_27_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_29_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_25_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_26_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_24_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_28_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_16_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_22_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_21_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_23_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_19_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-02 13:18:00,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_113_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_116_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_118_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_117_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_114_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: [2022-12-02 13:18:00,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-12-02 13:18:00,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_212_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_223_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-02 13:18:00,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +41: [2022-12-02 13:18:00,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt. + 1: [2022-12-02 13:18:00,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +41: [2022-12-02 13:18:00,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_74_mp_rank_01_optim_states.pt + 1: [2022-12-02 13:18:00,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_75_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_36_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt. +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_33_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_39_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_37_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_38_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_34_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_32_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_35_mp_rank_01_optim_states.pt +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +36: [2022-12-02 13:18:00,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:18:00,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_189_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,343] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_214_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,347] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,348] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_83_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,349] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_86_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,350] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,351] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,353] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_231_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,354] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt. +10: [2022-12-02 13:18:00,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,356] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_65_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_66_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_71_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_68_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,355] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_70_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:18:00,357] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,358] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,359] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_96_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_98_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_99_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_102_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_101_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,360] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_100_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_160_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_163_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_164_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_167_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_165_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_166_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_161_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_178_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_176_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_179_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_183_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_181_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_180_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,366] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,367] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,367] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,367] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_227_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,367] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_226_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,369] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,370] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,374] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,376] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,377] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +30: [2022-12-02 13:18:00,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,379] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,380] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_233_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt. + 1: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt. +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_146_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_147_mp_rank_01_optim_states.pt + 1: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_148_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_151_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_145_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_149_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_144_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_150_mp_rank_01_optim_states.pt +50: [2022-12-02 13:18:00,383] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +50: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,384] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt. +15: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +40: [2022-12-02 13:18:00,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_69_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +40: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:18:00,385] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_67_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt. +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_158_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_152_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_155_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_159_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_154_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_156_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_157_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_153_mp_rank_01_optim_states.pt +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +51: [2022-12-02 13:18:00,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:18:00,390] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt. +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_137_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_143_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_136_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_141_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_139_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_140_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_138_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_142_mp_rank_01_optim_states.pt +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +49: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:18:00,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +29: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_221_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-02 13:18:00,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_252_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_17_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_132_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_241_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:18:00,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_122_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_171_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_244_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-12-02 13:18:00,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:18:00,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:18:00,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:18:00,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,409] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,411] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_199_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,412] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt. + 1: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:18:00,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:18:00,415] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-02 13:18:00,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_112_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt. + 2: [2022-12-02 13:18:00,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +58: [2022-12-02 13:18:00,417] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_208_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:18:00,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:18:00,423] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_13_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_49_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,425] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,427] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +23: [2022-12-02 13:18:00,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-12-02 13:18:00,430] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-12-02 13:18:00,430] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,431] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_182_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,432] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_111_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,433] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_81_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,434] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_246_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:18:00,438] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,438] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +18: [2022-12-02 13:18:00,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,439] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,439] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,440] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_30_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +24: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +24: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-12-02 13:18:00,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +17: [2022-12-02 13:18:00,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_97_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt. +28: [2022-12-02 13:18:00,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +57: [2022-12-02 13:18:00,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_205_mp_rank_01_optim_states.pt +28: [2022-12-02 13:18:00,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +57: [2022-12-02 13:18:00,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_210_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_213_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-02 13:18:00,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_44_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +52: [2022-12-02 13:18:00,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt. +52: [2022-12-02 13:18:00,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_162_mp_rank_01_optim_states.pt +52: [2022-12-02 13:18:00,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +54: [2022-12-02 13:18:00,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt. +54: [2022-12-02 13:18:00,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_177_mp_rank_01_optim_states.pt +54: [2022-12-02 13:18:00,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 9: [2022-12-02 13:18:00,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-12-02 13:18:00,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-12-02 13:18:00,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +22: [2022-12-02 13:18:00,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +22: [2022-12-02 13:18:00,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +22: [2022-12-02 13:18:00,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +31: [2022-12-02 13:18:00,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-12-02 13:18:00,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-12-02 13:18:00,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +39: [2022-12-02 13:18:00,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt. +24: [2022-12-02 13:18:00,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +39: [2022-12-02 13:18:00,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_63_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +24: [2022-12-02 13:18:00,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +41: [2022-12-02 13:18:00,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt. +41: [2022-12-02 13:18:00,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_77_mp_rank_01_optim_states.pt +41: [2022-12-02 13:18:00,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +40: [2022-12-02 13:18:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt. +40: [2022-12-02 13:18:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_64_mp_rank_01_optim_states.pt +40: [2022-12-02 13:18:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:18:00,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_228_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-12-02 13:18:00,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-12-02 13:18:00,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt. +55: [2022-12-02 13:18:00,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_188_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_185_mp_rank_01_optim_states.pt +55: [2022-12-02 13:18:00,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +55: [2022-12-02 13:18:00,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:18:00,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +12: [2022-12-02 13:18:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-12-02 13:18:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-12-02 13:18:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_131_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 2: [2022-12-02 13:18:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-12-02 13:18:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-12-02 13:18:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt. +59: [2022-12-02 13:18:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_218_mp_rank_01_optim_states.pt +59: [2022-12-02 13:18:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +63: [2022-12-02 13:18:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt. +63: [2022-12-02 13:18:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_249_mp_rank_01_optim_states.pt +63: [2022-12-02 13:18:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +10: [2022-12-02 13:18:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +16: [2022-12-02 13:18:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-12-02 13:18:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-12-02 13:18:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_237_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_18_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_120_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_170_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +14: [2022-12-02 13:18:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-12-02 13:18:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-12-02 13:18:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +38: [2022-12-02 13:18:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt. +38: [2022-12-02 13:18:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_52_mp_rank_01_optim_states.pt +38: [2022-12-02 13:18:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +42: [2022-12-02 13:18:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt. +42: [2022-12-02 13:18:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_84_mp_rank_01_optim_states.pt +42: [2022-12-02 13:18:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +61: [2022-12-02 13:18:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt. +61: [2022-12-02 13:18:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_238_mp_rank_01_optim_states.pt +61: [2022-12-02 13:18:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +37: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt. +37: [2022-12-02 13:18:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_41_mp_rank_01_optim_states.pt +37: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt. +33: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt. +10: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-12-02 13:18:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +27: [2022-12-02 13:18:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-12-02 13:18:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-12-02 13:18:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +28: [2022-12-02 13:18:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-12-02 13:18:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-12-02 13:18:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +48: [2022-12-02 13:18:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt. +48: [2022-12-02 13:18:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_134_mp_rank_01_optim_states.pt +48: [2022-12-02 13:18:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +33: [2022-12-02 13:18:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_10_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_9_mp_rank_01_optim_states.pt +33: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +33: [2022-12-02 13:18:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +11: [2022-12-02 13:18:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-12-02 13:18:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +21: [2022-12-02 13:18:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-12-02 13:18:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-12-02 13:18:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_192_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_89_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +34: [2022-12-02 13:18:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt. +34: [2022-12-02 13:18:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_20_mp_rank_01_optim_states.pt +34: [2022-12-02 13:18:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +47: [2022-12-02 13:18:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt. +47: [2022-12-02 13:18:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_123_mp_rank_01_optim_states.pt +47: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +60: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt. +60: [2022-12-02 13:18:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_230_mp_rank_01_optim_states.pt +60: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt. +45: [2022-12-02 13:18:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_110_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_108_mp_rank_01_optim_states.pt +45: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +45: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +20: [2022-12-02 13:18:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-12-02 13:18:00,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-12-02 13:18:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +19: [2022-12-02 13:18:00,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-12-02 13:18:00,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-12-02 13:18:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 1: [2022-12-02 13:18:00,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-12-02 13:18:00,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-12-02 13:18:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-02 13:18:00,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt. +46: [2022-12-02 13:18:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_115_mp_rank_01_optim_states.pt +46: [2022-12-02 13:18:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 8: [2022-12-02 13:18:00,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-12-02 13:18:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-12-02 13:18:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +62: [2022-12-02 13:18:00,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt. +62: [2022-12-02 13:18:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_243_mp_rank_01_optim_states.pt +62: [2022-12-02 13:18:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +59: [2022-12-02 13:18:00,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt. + 5: [2022-12-02 13:18:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +59: [2022-12-02 13:18:00,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_219_mp_rank_01_optim_states.pt + 5: [2022-12-02 13:18:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +59: [2022-12-02 13:18:00,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 5: [2022-12-02 13:18:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-12-02 13:18:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +13: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 6: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-12-02 13:18:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +46: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt. + 4: [2022-12-02 13:18:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +46: [2022-12-02 13:18:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_119_mp_rank_01_optim_states.pt + 4: [2022-12-02 13:18:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +46: [2022-12-02 13:18:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +39: [2022-12-02 13:18:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt. +39: [2022-12-02 13:18:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_59_mp_rank_01_optim_states.pt +39: [2022-12-02 13:18:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +35: [2022-12-02 13:18:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt. +35: [2022-12-02 13:18:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_31_mp_rank_01_optim_states.pt +35: [2022-12-02 13:18:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +56: [2022-12-02 13:18:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt. +56: [2022-12-02 13:18:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_193_mp_rank_01_optim_states.pt +56: [2022-12-02 13:18:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +53: [2022-12-02 13:18:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt. +53: [2022-12-02 13:18:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_172_mp_rank_01_optim_states.pt +53: [2022-12-02 13:18:00,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +44: [2022-12-02 13:18:00,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt. +44: [2022-12-02 13:18:00,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_103_mp_rank_01_optim_states.pt +44: [2022-12-02 13:18:00,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 7: [2022-12-02 13:18:00,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-12-02 13:18:00,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-12-02 13:18:00,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +43: [2022-12-02 13:18:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt. +43: [2022-12-02 13:18:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_94_mp_rank_01_optim_states.pt +43: [2022-12-02 13:18:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +15: [2022-12-02 13:18:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-12-02 13:18:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-12-02 13:18:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +26: [2022-12-02 13:18:00,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-12-02 13:18:00,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-12-02 13:18:00,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_211_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 3: [2022-12-02 13:18:00,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-12-02 13:18:00,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-12-02 13:18:00,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +25: [2022-12-02 13:18:00,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-12-02 13:18:00,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-12-02 13:18:00,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 4: [2022-12-02 13:18:00,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-12-02 13:18:00,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-12-02 13:18:00,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! +58: [2022-12-02 13:18:00,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt. +58: [2022-12-02 13:18:00,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_3b977b/global_step73814/bf16_zero_pp_rank_215_mp_rank_01_optim_states.pt +58: [2022-12-02 13:18:00,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step73814 is ready now! + 0: successfully saved checkpoint at iteration 73814 to checkpoints_3b977b +63: ------------------------------------------------------------------------------------------------------------ +63: test loss at the end of training for test data | lm loss value: 1.817317E+00 | lm loss PPL: 6.155322E+00 | +63: ------------------------------------------------------------------------------------------------------------ +END 2100040: Fri Dec 2 13:18:17 EET 2022 diff --git a/3b977b77b/sbatch_3b9_77b.sh b/3b977b77b/sbatch_3b9_77b.sh new file mode 100644 index 0000000000000000000000000000000000000000..bdb36cd1d184ca1d02bfc0418493b9ec1e914245 --- /dev/null +++ b/3b977b77b/sbatch_3b9_77b.sh @@ -0,0 +1,159 @@ +#!/bin/bash +#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901 +#SBATCH --nodes=64 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p pilot +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=3b977b + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document" + +PP_SIZE=2 +TP_SIZE=1 + +MICRO_BATCH_SIZE=1 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_4084M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=10000 + +# Tokens: 77_400_000_000 +# -> Samples: 37792969 +TRAIN_SAMPLES=37_792_969 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 377_930 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/3b977b77b/tensorboard/events.out.tfevents.1669792911.nid005755.14697.0 b/3b977b77b/tensorboard/events.out.tfevents.1669792911.nid005755.14697.0 new file mode 100644 index 0000000000000000000000000000000000000000..83cffdccb9dad52f82044b650640fddfdc95a6a3 --- /dev/null +++ b/3b977b77b/tensorboard/events.out.tfevents.1669792911.nid005755.14697.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9151a1a1ee0e3d704747347eeca2a7f9b91451bafeae8d8911131392094645b +size 19356 diff --git a/3b977b77b/tensorboard/events.out.tfevents.1669793631.nid005755.23535.0 b/3b977b77b/tensorboard/events.out.tfevents.1669793631.nid005755.23535.0 new file mode 100644 index 0000000000000000000000000000000000000000..90c39f391485d7bdc9ad894528dd8a8bcaa16166 --- /dev/null +++ b/3b977b77b/tensorboard/events.out.tfevents.1669793631.nid005755.23535.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a379453fb5306f47917452cd7735435f9f1a150736b29a785ce6d802a5668819 +size 132053985 diff --git a/3b977b77b/tensorboard/events.out.tfevents.1669970792.nid006887.130794.0 b/3b977b77b/tensorboard/events.out.tfevents.1669970792.nid006887.130794.0 new file mode 100644 index 0000000000000000000000000000000000000000..004c92b991a40dad649f98a4ac445cb3925c8891 --- /dev/null +++ b/3b977b77b/tensorboard/events.out.tfevents.1669970792.nid006887.130794.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c2327ecdf132d16b8b49fe11b85e1d31d058a404d26a538fa6cd292e2411b5 +size 6874987 diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.json new file mode 100644 index 0000000000000000000000000000000000000000..66f90d5c6a3845a0831cd9446488e855add2ae01 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.2882702237124178, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03507359582313697}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07300904609224831, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0029525045593291944}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.23319598837092428, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004717928243407737}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.09304445819797845, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021071281123058827}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.031781240194588535, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001647655179664631}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.11446696473056167, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0030078380901265153}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.04357651166126725, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0012628931036486493}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.07148927214916825, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0028994443219541085}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.22962123752434357, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004651057204662988}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.09113938986614295, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002025825990715642}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06999428575198861, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029010892622887635}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.22168579525487217, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0043756801267272015}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08853812013819903, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019810527750856927}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.json new file mode 100644 index 0000000000000000000000000000000000000000..a4f0f49fa0f1bcaa70cbf6c5a5fbee1ffa21ec6e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.22276279918601394, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.018133211573574757}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06067991294954199, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002071772799498889}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.20293836364892254, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004213962706134935}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.0827185269757938, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001999403821307096}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.02515093170386624, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0012657693333304634}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.0927272131857222, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00270796998310677}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.03533725838532431, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011679547214428377}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.05782243575115753, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0019660354949123677}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.19744065879364792, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004113784957628094}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.07920096600543666, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018627056924898366}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.05802381954191155, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0019924692015719286}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.19618466537860657, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0040253079050866485}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.07922447831134258, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018815454632281374}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.json new file mode 100644 index 0000000000000000000000000000000000000000..66dadc726634bb401d2e7855b06bfcdc21dab2b5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.22816452014689217, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.021011094086360756}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0643252880050605, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001873211164048415}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.21568616317061653, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004082948724364347}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.0888316472488794, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002008077222359181}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.02624513151161159, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001151855832984562}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.09761833567947041, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0026995300080965585}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.03698279772417711, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011212628433211664}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.0606248912817486, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001701220213613193}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.20937007549926187, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003993668186702462}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.08454134203955807, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018430886624515794}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06105372863643947, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001737959743755711}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.20931532337002748, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003964000228350047}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08484366265533932, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018647506310172767}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8bcc3cc87e906c3febb8359f2963db90ae5ef990 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.21668033919612437, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.020179750003043416}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06599850329511878, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0020196888536449255}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.2189549242330715, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00402494120221226}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.09037007800347752, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021075393335480913}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.026861010489235518, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010411924138277121}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.09848799682900536, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002619448977397938}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.037900350601950995, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011762008290810827}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.0616752271189791, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017718026569788809}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.2115279407271533, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0038925777592653194}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.0854553995007257, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018898385438172103}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.0623910245818171, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018474876713692014}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.2116287101661098, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0038714328117695138}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08596309183671783, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001927157623088893}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c42cda8bdf40ad1f433102b837556d6159ea75b7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.22324841354029434, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.012884365211201858}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06502648081363527, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019568795906677195}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.22314967057311585, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004060178019176997}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.08984024388721441, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002049686525188311}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.027172974346249407, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010775269042031367}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.10278841213516382, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0026896302440292856}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.038427620423283494, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011342309564967815}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06051581313878435, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001686918901782139}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.21546541192297525, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0039050941983854084}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.08475169911603465, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018041950412597118}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06149322300624985, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017642592919849167}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.21601509705224456, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003902368298687872}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08562046048144208, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018622202648950923}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.json new file mode 100644 index 0000000000000000000000000000000000000000..0584d3ef8a22683cdaac0b6a8c40069b1f2c7ffa --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.21464230162703427, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.01244691129274461}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06952443270444716, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0022809171687925307}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.23024280021949023, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00409858662928981}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.09216278427137457, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002102114353680242}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.027750881647517683, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011006386822245205}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.10600678669436031, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002763944580059492}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.03892365918376217, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011826072971332408}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06485734355722127, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002020231716412655}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.22257612852322436, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003940687874091731}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.08717550041439592, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018759391818764337}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06592417348285784, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0021091163919465493}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.22298794088967588, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003928367080650771}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08796230830100418, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019209922626217265}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b5d44babdfd725d4112ce4baa46fbd9a24a10832 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_precision": 0.007871384048100007, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0008027273679290646}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_recall": 0.025894899249411275, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001510927848658749}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_fmeasure": 0.007735199321992511, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0004929168751900662}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_precision": 0.00018612440324107684, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00010813827959713304}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_recall": 0.00113072926486338, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0002538916851940024}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_fmeasure": 0.00024213283343663074, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00010293363022896083}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_precision": 0.007831916501187445, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0007926431382581877}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_recall": 0.02584550434779307, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0015047949229976157}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_fmeasure": 0.007693913912486717, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00047606068305271974}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_precision": 0.006437589464226677, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0007714572173800608}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_recall": 0.018623470093568916, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0011493529601984355}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_fmeasure": 0.0054174592644268636, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0003711886426354486}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "bleu": 0.002413992658676713, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.00013676206143739094}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.json new file mode 100644 index 0000000000000000000000000000000000000000..7662c72734497ae35e0a138c498958807d6bf4a6 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_precision": 0.17162164691878115, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002541153433910131}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_recall": 0.1570833115237782, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0023628047156862182}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_fmeasure": 0.14455688747960732, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0018065881001650948}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_precision": 0.017746162480695066, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011795108909179546}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_recall": 0.01659075032220689, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0010082231571640825}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_fmeasure": 0.014443686344970957, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0008315132954917715}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_precision": 0.14445360743779065, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0021746805211461384}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_recall": 0.13201397388417854, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019716702901784876}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_fmeasure": 0.12055575191673172, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014352825043199523}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_precision": 0.1529221545748428, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002295493453246678}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_recall": 0.13941491139639123, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0020642758193953298}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_fmeasure": 0.12789813539780287, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0015529949122606935}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "bleu": 0.7346171507567223, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.13707913782304798}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d941447983bad1f3b33de5444e3f262c5b58757f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_precision": 0.20663907836610496, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0033829599247524127}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_recall": 0.2479349663972334, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0044131481989255214}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_fmeasure": 0.18740801320012218, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0026759273447015666}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_precision": 0.044514823553754815, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0020773970237284085}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_recall": 0.06392575894949451, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002576650238805862}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_fmeasure": 0.04163806201461763, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001744964461999939}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_precision": 0.17383935881323387, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0029141796169836406}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_recall": 0.21185220120183285, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00391960722018384}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_fmeasure": 0.15705135749100313, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0022404431287739728}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_precision": 0.18333789821164648, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0030290826006994917}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_recall": 0.2176069260272544, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003804234575122432}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_fmeasure": 0.16490115686406231, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0023344806701187824}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "bleu": 0.8566894201349882, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08624072055130635}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.json new file mode 100644 index 0000000000000000000000000000000000000000..4a807abe12dd5aecdab7ce41cf0a4a5942eabf5e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_precision": 0.23700393129285693, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003998832100987239}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_recall": 0.26444744204782306, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004491563559631609}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_fmeasure": 0.20662215475852175, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0029093584177742257}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_precision": 0.0618205621459243, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0025531310938124367}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_recall": 0.07796583472925955, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0027407400714859207}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_fmeasure": 0.05445999669995589, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00197546840586398}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_precision": 0.1993414050245294, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0034880359309727806}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_recall": 0.2262831386525155, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004000931690515669}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_fmeasure": 0.1731669889234156, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0024412054531090356}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_precision": 0.21007336129721205, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003603119181953105}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_recall": 0.23246013837952773, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003889246478806612}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_fmeasure": 0.18190324751556092, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002538737343530949}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "bleu": 1.0569147515296082, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0894097345506189}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.json new file mode 100644 index 0000000000000000000000000000000000000000..41a7f784559f5670effdeb6e170311b45017a5ee --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_precision": 0.24343442215612912, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004290336159466549}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_recall": 0.2937677188486643, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00476022029269311}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_fmeasure": 0.21768757196984853, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0030964308114536637}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_precision": 0.07382521753054258, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002822725067559204}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_recall": 0.09629906393146742, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0030384383273633826}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_fmeasure": 0.06572301772314433, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0022002247062358235}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_precision": 0.2052733017686618, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0037268495898633647}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_recall": 0.252355975266905, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004227144384953933}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_fmeasure": 0.18281448217767138, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002566640286607954}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_precision": 0.21562448887139193, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003855934210118673}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_recall": 0.2578416353472927, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004098132845796672}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_fmeasure": 0.1915680837153, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0026965258074827755}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "bleu": 1.1744154279568062, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.10900900384288126}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.json new file mode 100644 index 0000000000000000000000000000000000000000..08fa79ee2563f356a7263821eaa6cd3ae39d3327 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_precision": 0.25749968628071634, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004557872484881917}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_recall": 0.2952708397989195, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004728252484609096}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge1_fmeasure": 0.22576005910143196, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0032791573262992177}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_precision": 0.08269685100109506, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.003027333731786083}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_recall": 0.10110655349024573, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0031054606964476387}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rouge2_fmeasure": 0.07189912423622183, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0023282015023082664}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_precision": 0.21853685082560628, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0039871118588556366}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_recall": 0.25492080968482705, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00420711638229053}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeL_fmeasure": 0.19074926578003074, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0027348190562132136}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_precision": 0.22916016865925895, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00411577700341045}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_recall": 0.260297323377531, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00409556008633347}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "rougeLsum_fmeasure": 0.19945385414430314, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0028579749339794932}, {"task_name": "GEM/web_nlg_en", "prompt_name": "explicit-graph-description2", "bleu": 1.2744890026821296, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "afeec167-f75f-4687-a775-1efde7d04780", "prompt_jinja": "{{input | join(\", \")}}. \n\nThe above is a set of subject | predicate | object expressions separated by commas: \nWrite all the information in proper sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09553029750807113}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.json new file mode 100644 index 0000000000000000000000000000000000000000..6169f872615a459b7e71aca55fa8aa3d9b3fda71 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "bleu": 0.138569878297038, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.031551101184468404}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_precision": 0.03724302186557898, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0022152532951271718}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_recall": 0.22526135818945897, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003344792850841178}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_fmeasure": 0.04792939313815056, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0009615050147245499}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_precision": 0.005393881463397369, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0003489838735994459}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_recall": 0.04305719338313865, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0019680551642618054}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_fmeasure": 0.008626127762314056, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0004981474293610044}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_precision": 0.03600954286370912, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0021750052445456717}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_recall": 0.22113346749553864, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0032963184671457187}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_fmeasure": 0.046408969912627086, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008900420023077054}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_precision": 0.0326382629292867, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002191301787071691}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_recall": 0.18954584534668284, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028756146093179826}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_fmeasure": 0.040241405686779766, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0008508436852286362}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d3ae02e3326b683bbc59efbefbe03ee276b5a543 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "bleu": 0.7190193263389013, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.13634910774619252}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_precision": 0.1677909378471085, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0025279575952143075}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_recall": 0.1557256533318373, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024294408093670523}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_fmeasure": 0.14139180219702063, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001814619491045361}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_precision": 0.016973478974085843, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011314265139906986}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_recall": 0.01638165201377114, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009960548800777898}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_fmeasure": 0.01386135386977246, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007977730891733734}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_precision": 0.14118769936973508, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0021616686394079765}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_recall": 0.1311490160490549, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0020570345011630387}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_fmeasure": 0.11787997771951876, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014405006728974714}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_precision": 0.14939682437853644, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0022883954744429844}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_recall": 0.1379569195179203, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002111952939893884}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_fmeasure": 0.12499033357696115, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0015650259493247992}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.json new file mode 100644 index 0000000000000000000000000000000000000000..3f233837e9e9d379d4f48794bae5f87549e86078 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "bleu": 0.654858159962283, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05090283227203148}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_precision": 0.18587109175652072, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0032528462646382837}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_recall": 0.25339458245702867, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004577585923235268}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_fmeasure": 0.1718578502584956, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00246372252095823}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_precision": 0.038492631218654094, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0018039997248216703}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_recall": 0.0713821989527362, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0027007946811370516}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_fmeasure": 0.03832506645342158, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0014998680640168213}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_precision": 0.1565380855202379, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002747157296710683}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_recall": 0.22294560743499395, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004308467347707439}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_fmeasure": 0.14549486942641893, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0020319539502286887}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_precision": 0.16369817034532635, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0028970310154362226}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_recall": 0.22068224654084853, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0039045572017400235}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_fmeasure": 0.14994420152341253, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002110161728007287}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.json new file mode 100644 index 0000000000000000000000000000000000000000..bb6787a81b95aaba48018276fbb402cc00462513 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "bleu": 0.8662810235466556, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09404503161396437}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_precision": 0.21630507113127517, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0037635681346209204}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_recall": 0.29385220234946363, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004939943721033626}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_fmeasure": 0.19757579221778704, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002740581812349554}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_precision": 0.05540012459456432, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002226210322926932}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_recall": 0.09790333465592813, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003133062562474596}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_fmeasure": 0.05353042851216683, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0018154897675158883}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_precision": 0.1839111737113415, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0032708663113493845}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_recall": 0.2610670692827167, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004730435390915318}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_fmeasure": 0.1686567646585531, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00233205958797479}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_precision": 0.19108993104157018, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00343247374642446}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_recall": 0.25510045795061914, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004229656468015747}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_fmeasure": 0.17281728476431374, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002423817934865248}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.json new file mode 100644 index 0000000000000000000000000000000000000000..aaf09ba83e5c4e8a4e00a0ff45cddfd22be5e4b6 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "bleu": 0.8327592530541046, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08252044356912364}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_precision": 0.22591578566077025, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0040744177303127975}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_recall": 0.3271371159734268, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004954912621561014}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_fmeasure": 0.20994644193209497, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002856480485934521}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_precision": 0.06610289029069367, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0024587911594638476}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_recall": 0.11815894609420728, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003294870975442443}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_fmeasure": 0.06406636511396212, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001978008075438107}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_precision": 0.19179087245553803, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0034654596797486763}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_recall": 0.29163613239456493, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004772453186076372}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_fmeasure": 0.1795827877529302, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0024101179259044926}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_precision": 0.1981303722652317, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0036291877325131637}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_recall": 0.28411489421280556, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004268909617622095}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_fmeasure": 0.18295052341283213, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0025224970561372752}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.json new file mode 100644 index 0000000000000000000000000000000000000000..dd3141824f53c9db24fff46ba8705b2bbc60e8b0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "bleu": 0.9864896153661107, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1114488450591458}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_precision": 0.24687269679032836, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004501369815547214}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_recall": 0.3404419977444704, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005025782336662627}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge1_fmeasure": 0.2239773930782515, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.003099702038886262}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_precision": 0.08027601856562787, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0028587155748841155}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_recall": 0.12944258320105298, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0033520136379546575}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rouge2_fmeasure": 0.07459291610833325, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0021594277862978053}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_precision": 0.21029176429912327, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.003853857396675998}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_recall": 0.3046329495523381, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004807937355834806}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeL_fmeasure": 0.1924435416395898, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0026000922872309144}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_precision": 0.21773348211753543, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004056669090372054}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_recall": 0.29668821393068523, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004287898580495838}, {"task_name": "GEM/web_nlg_en", "prompt_name": "implicit-graph-description", "rougeLsum_fmeasure": 0.19609167052374815, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "38342608-5cd7-4ce7-b2e1-905ecd7f4c80", "prompt_jinja": "{{input | join(\"; \")}}\nThe above is a collection of relations. Write descriptive English that contains this information.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0027163034898814884}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.json new file mode 100644 index 0000000000000000000000000000000000000000..507332ff3a3cb07973c4b4d0cf9f78ae59565d37 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_precision": 0.03974548833329957, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0016187665175497782}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_recall": 0.14319286698789227, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002689949685516924}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_fmeasure": 0.051963445903168815, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001030164799332613}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_precision": 0.0032603459694508664, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00035703887248090323}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_recall": 0.015671514326625717, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001194008851035889}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_fmeasure": 0.004924022976700059, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00046504584059277863}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_precision": 0.03627088781319514, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0015426070426077998}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_recall": 0.1339405385147445, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025465644416711453}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_fmeasure": 0.04746954821622165, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008839674059173651}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_precision": 0.036598894332640367, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015865773575606916}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_recall": 0.12773491888135802, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022633071599434925}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_fmeasure": 0.04700320033377673, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0009162627771699139}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "bleu": 0.10593475044710148, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.02687963406061457}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.json new file mode 100644 index 0000000000000000000000000000000000000000..23e6a52abf7e99862efdc121c568e2f7d107e965 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_precision": 0.1735967063811906, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0026270802204174095}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_recall": 0.17887650999515012, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0031318162204511425}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_fmeasure": 0.15066523178744332, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001954438625710324}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_precision": 0.021433820753724266, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001247407681297529}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_recall": 0.029129370749806007, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016832821472482552}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_fmeasure": 0.01960777337004029, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001029143211904409}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_precision": 0.14613868593964888, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002258852219739637}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_recall": 0.15296643190709636, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002859088570123784}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_fmeasure": 0.12623806450553654, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016066368664537727}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_precision": 0.15418999276855516, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002386058978805089}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_recall": 0.15812304797391522, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0027464038170145967}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_fmeasure": 0.13299010686343601, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001711708966298464}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "bleu": 0.866182823458432, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.12067272006028423}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a03db9aaef7207121ef2f988581115690ea1faf2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_precision": 0.18939988211510023, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003015336802954258}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_recall": 0.21147314525622352, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003724259557883497}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_fmeasure": 0.16765923923678647, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022559374477986185}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_precision": 0.03379022133984764, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0017843702674752064}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_recall": 0.04784569405826686, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002202164940653821}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_fmeasure": 0.03131581713976908, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0014111826750632776}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_precision": 0.1598064546454118, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002629394580363481}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_recall": 0.18237543607435028, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0034360872181296307}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_fmeasure": 0.14117220655320378, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018990556078266275}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_precision": 0.16876738068884203, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0027439682577306787}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_recall": 0.18685899221940896, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0032539799319502814}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_fmeasure": 0.14809597509839093, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001972913231852908}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "bleu": 0.8730659372849066, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0967542162395743}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d25fa99962e33dd1d63d913d1d0eab50319cb8b0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_precision": 0.20206518395397247, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0033815561981644514}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_recall": 0.22055576804184665, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0038689842229781995}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_fmeasure": 0.17604709161678792, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0024207021911546002}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_precision": 0.042414826534170676, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002194212193720834}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_recall": 0.056638379731478804, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0024560943269569097}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_fmeasure": 0.03774742782188923, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016476754720179338}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_precision": 0.17012750089049355, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002909118143288585}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_recall": 0.19153932535514462, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0036627963511066176}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_fmeasure": 0.1484395491444522, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0020503728880959028}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_precision": 0.18026184477100235, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0030566342359595712}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_recall": 0.19503635904047142, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00336915844462403}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_fmeasure": 0.15595031738973972, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0021234132418142156}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "bleu": 1.2329509109603611, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.17037107794770673}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.json new file mode 100644 index 0000000000000000000000000000000000000000..70ecfff822fa071ba3685f2c84c1ee896d9c30d0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_precision": 0.21304666535883363, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0035447207581696576}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_recall": 0.24044196270498344, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0041272020875937985}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_fmeasure": 0.1877008682716093, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0025984841921980026}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_precision": 0.05150741153389857, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002310685514094819}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_recall": 0.06873712069242928, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002686212129477722}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_fmeasure": 0.04618308258359416, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001794744112452255}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_precision": 0.18100550700598406, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00309059853405147}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_recall": 0.2097555633903283, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0038640348862670876}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_fmeasure": 0.15952145174338822, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002218483952497624}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_precision": 0.18979889801871716, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003258591536788394}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_recall": 0.2114319997150186, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0035621450472765647}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_fmeasure": 0.16563209206374943, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002290227287484681}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "bleu": 1.0792721560875334, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11897941335086845}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2cdfb1b5be642e92b9f7c365f95a6098d62820e2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_precision": 0.22377177397658685, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003751306840404075}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_recall": 0.24374911073515992, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004063940123637665}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge1_fmeasure": 0.1937895542833093, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0026930519639634374}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_precision": 0.05842395909971782, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002544233000490118}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_recall": 0.07447247779662981, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0027180704781684995}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rouge2_fmeasure": 0.05181468037449851, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0019301208843236668}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_precision": 0.19087203826268628, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.003283058254228487}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_recall": 0.21393350174137546, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003813517852998068}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeL_fmeasure": 0.16586855159557498, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002321441985077457}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_precision": 0.2003884829724675, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00343390307735665}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_recall": 0.21705758718159215, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0035797162130504407}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "rougeLsum_fmeasure": 0.17256400094312105, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002384598354184546}, {"task_name": "GEM/web_nlg_en", "prompt_name": "non-explicit-description", "bleu": 1.0840527290308135, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "9415bd8a-685f-4fa4-803a-f09bd47d4603", "prompt_jinja": "I am taking this tabular data, where each row is separated by a \"|\" and expresses a relation between an object and a predicate : {{input | join(\", \")}}. \n\nNow, I will produce a description of the tabular data using English sentences. {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1285257175145367}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e2cbb7b6188a8770326edf42ec424132b273d113 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_precision": 0.11575198382455341, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017409474424184654}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_recall": 0.608459061007921, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003019908683780843}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_fmeasure": 0.1845095102209193, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022693042573866838}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_precision": 0.04666714418190469, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009925004787402806}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_recall": 0.25929817858149656, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0031405181722228706}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_fmeasure": 0.07462288276980816, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0013694868585983554}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_precision": 0.09923197095834116, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012283545567891168}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_recall": 0.5587128288782699, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003317057185320759}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_fmeasure": 0.16027950358425136, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016115627858449338}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_precision": 0.09697095057432645, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015588062714270727}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_recall": 0.5092192403982401, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028311576287597846}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_fmeasure": 0.15437018471820735, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0020528117868010066}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "bleu": 0.80522341763869, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08331054875537132}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.json new file mode 100644 index 0000000000000000000000000000000000000000..5975ddbaec9ce742eff28031c325427cd2ddebd1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_precision": 0.19174924772721366, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0032940489896208926}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_recall": 0.2698784746776444, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004773612866682941}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_fmeasure": 0.1835504434103257, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002742918027631955}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_precision": 0.04272035087355504, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0019901580959531236}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_recall": 0.08265565051963014, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0030886698848430383}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_fmeasure": 0.04520576758964237, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0018353621819071602}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_precision": 0.1601819681970939, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027461365015910427}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_recall": 0.23680658224270798, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004517480324960939}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_fmeasure": 0.15410415993634588, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0022370627269454606}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_precision": 0.16856045163213934, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00294994820031969}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_recall": 0.2363719127409182, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004152500838774223}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_fmeasure": 0.16046862402135503, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002398180973300977}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "bleu": 0.9786465584605349, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.14122810214566986}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.json new file mode 100644 index 0000000000000000000000000000000000000000..074b597e129b731bff685f4a02cea5fecfe50c06 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_precision": 0.20221739794884294, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0035499636350329366}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_recall": 0.3332186264589581, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005170101384807238}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_fmeasure": 0.1992879161350844, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002645957854064047}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_precision": 0.05936354342280888, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002387647853920241}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_recall": 0.1225094044913992, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0034016962379593376}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_fmeasure": 0.06125938231479426, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0018555518510493417}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_precision": 0.1735345422105144, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.003136069929113322}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_recall": 0.29921178664666864, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00498953624810007}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_fmeasure": 0.17221690830374237, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0022796430855117032}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_precision": 0.17949949840259782, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003267322153420465}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_recall": 0.29229470206548336, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004488431177710736}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_fmeasure": 0.17513713323826788, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0023508381923365734}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "bleu": 0.8880569236257283, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.10425228469519156}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.json new file mode 100644 index 0000000000000000000000000000000000000000..46b47a362d1d38dfa98dfae485910cabab804fa1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_precision": 0.22015440449805468, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004191773103751877}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_recall": 0.36592032189171225, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005068220370589984}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_fmeasure": 0.21408595760940946, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002783818736006089}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_precision": 0.07910542573583534, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0029902820037111502}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_recall": 0.1491354669018872, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003459225616571808}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_fmeasure": 0.07696626766564611, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0020398698531970743}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_precision": 0.19072950772310418, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.003726367705712794}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_recall": 0.33282521900185674, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004954398958565515}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_fmeasure": 0.18711621313587448, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0024249095985234463}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_precision": 0.1958992768265335, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003884089051877238}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_recall": 0.3218771452899728, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004412820950063993}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_fmeasure": 0.1889169148591612, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0025246051964903276}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "bleu": 0.9859334350527383, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09896199153842244}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.json new file mode 100644 index 0000000000000000000000000000000000000000..0e41ca5b928139fbb549338061e92828df52e62c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_precision": 0.23228499942428968, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004398241056245007}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_recall": 0.38453431214088857, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.005025202128638685}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_fmeasure": 0.22549673923508326, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002910775643802205}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_precision": 0.08911780913376037, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0031127641641959516}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_recall": 0.16391169232553854, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.003564158188179595}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_fmeasure": 0.08622184894243098, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.002115033774398341}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_precision": 0.20268160388419554, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0039238158298998795}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_recall": 0.3506485664858236, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004886831999021539}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_fmeasure": 0.19820026126581727, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002503140302475953}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_precision": 0.20731340856698283, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004088067992288368}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_recall": 0.33831857306922314, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004362271840091005}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_fmeasure": 0.19907520284773375, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002614354718088979}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "bleu": 0.970241931626179, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09819030681966434}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.json new file mode 100644 index 0000000000000000000000000000000000000000..926849fb77b8568bd2dd0b8a851dc9ffc4d2f6e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_precision": 0.2382691545863073, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.004756985829441475}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_recall": 0.3912072250236538, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004984269579179742}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge1_fmeasure": 0.22840858338472744, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0030840481426459535}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_precision": 0.09843522450433298, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.003424552765398845}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_recall": 0.17269348031155235, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0035758918530598553}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rouge2_fmeasure": 0.09172527737837707, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0022023809206421522}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_precision": 0.20797653399558047, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00422832319942412}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_recall": 0.35688189171657314, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.004844058830738807}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeL_fmeasure": 0.2006439166198059, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.002601338113671856}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_precision": 0.21340003515373943, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.004405460746761557}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_recall": 0.3469582914902356, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.004377091064495331}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "rougeLsum_fmeasure": 0.20278396643749147, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002742019476188682}, {"task_name": "GEM/web_nlg_en", "prompt_name": "very-explicit-description", "bleu": 1.0632385816538097, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "426b682e-e801-4e8d-9ac3-5b676c9d3da2", "prompt_jinja": "A semantic triple is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a set of three entities that codifies a statement about semantic data in the form of subject\u2013predicate\u2013object expressions. (e.g., \"Bob | is | 35\", or \"Bob | knows | John\"). \n\nA graph can be formed from a set of these triples. An example is {{input | join(\", \")}}. \n\nWrite grammatical text expressing all the relations succinctly and fluently.\n{% for i in references %}\n ||| {{ i }} \n{% endfor %}\n\n", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.108635681810979}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..88881a9e38384270f2fe3d1c36770b78bc3b5353 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_precision": 0.195566960716181, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019276846426063785}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_recall": 0.3533886371026647, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0027880868773002996}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_fmeasure": 0.23412884345862264, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0018096388944563407}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_precision": 0.04589459114508951, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008493337249853646}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_recall": 0.08686815821286678, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017485584142853405}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_fmeasure": 0.05530555190416877, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009620765372106006}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_precision": 0.12997894688819828, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001176996687844147}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_recall": 0.2455653248515433, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002216289748634435}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_fmeasure": 0.1577035391779481, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0011540548708147851}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_precision": 0.18107871658618507, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017806857113047642}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_recall": 0.3283060348710063, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002625017894293712}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_fmeasure": 0.21698957847628453, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001673828218441473}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "bleu": 2.4682328449343904, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07088258721604575}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..755e20aaf3d9554decde4fe03dfc5bc24fc24c83 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_precision": 0.15627750165547535, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001962386369273289}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_recall": 0.2525742254443488, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003113402494824898}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_fmeasure": 0.17453230736185904, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001969765354449983}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_precision": 0.029169479431573355, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007882937343141538}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_recall": 0.0531848239381476, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015457168877853818}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_fmeasure": 0.03409011634055016, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0008690874010719925}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_precision": 0.11201479367079172, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001306085160918015}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_recall": 0.1848814168046244, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0023307923443449947}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_fmeasure": 0.1250045596802973, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012753773488612319}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_precision": 0.14621744079984547, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018210021156558275}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_recall": 0.23601641233060858, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028953510119446627}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_fmeasure": 0.16303218310550338, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018145396789941985}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "bleu": 1.7919407346163008, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0737452533520425}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6dcf9b2577c38761d79b8fb669456921037d2b72 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_precision": 0.14501437881859028, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019433084591004713}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_recall": 0.22467032769033468, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0029784346495177407}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_fmeasure": 0.15863525455004393, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001916917232761661}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_precision": 0.02442996212535727, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007519260848068276}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_recall": 0.042424873953699184, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0013993567734203126}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_fmeasure": 0.02797037755556898, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000824659834492331}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_precision": 0.10658397240465457, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013324023033187138}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_recall": 0.1684211774861765, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0022097636904149756}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_fmeasure": 0.11668679312793952, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001279584145980854}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_precision": 0.1356637096139804, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001799350424574685}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_recall": 0.20992335195224027, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0027445156356427094}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_fmeasure": 0.1482203100115215, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017644287180480047}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "bleu": 1.51129197235676, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.053033171757604795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..724212373500f50427bb767eebb3366928232bb6 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_precision": 0.12488990987685827, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0022261432116102544}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_recall": 0.18139575994673116, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0030867748398314713}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_fmeasure": 0.12879034116675933, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002014213748068574}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_precision": 0.020587304073537236, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008430364325238309}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_recall": 0.03345951804642443, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0013102881750652396}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_fmeasure": 0.02198351222980969, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007661410803321813}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_precision": 0.09378166940289302, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0016774718846480157}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_recall": 0.1378319099477178, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002341101765656631}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_fmeasure": 0.09609151005725931, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014143522793016892}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_precision": 0.116314348038094, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0020844285519718204}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_recall": 0.16840969828764962, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028496816197026674}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_fmeasure": 0.1195876958441179, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018550103716636955}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "bleu": 1.4186659295702861, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.050267910728881454}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ec9d21578d38e3f57655cbf879d778cab6eb2378 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_precision": 0.04274798462927153, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018161718038238448}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_recall": 0.05867994619730172, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002374781099841643}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_fmeasure": 0.04085144274673853, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001538442204027294}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_precision": 0.006984195242455265, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000603809740571673}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_recall": 0.011817282399442079, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009217929633034777}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_fmeasure": 0.0071615346459846605, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0004694288024279032}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_precision": 0.0331311683624868, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001416652850979173}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_recall": 0.04606968779468327, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0018746567174795128}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_fmeasure": 0.031403237162404916, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0011428460910517797}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_precision": 0.039597785262755085, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0016586096902770702}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_recall": 0.05473786135131624, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022121499800027366}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_fmeasure": 0.03803522378880029, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0014259840855105786}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "bleu": 0.18764755097372476, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0204323879125267}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..29901b9afdab7bac6669b7bc734697ad4d0055a0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_precision": 0.006928543414105365, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0008521915511742353}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_recall": 0.00867185146550297, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0010332808843393272}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge1_fmeasure": 0.005950641245994375, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006411674676836966}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_precision": 0.001396425548191038, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0003008386819272615}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_recall": 0.0020329927104609604, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00048577777702315096}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rouge2_fmeasure": 0.0011656375598739542, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002028046057963131}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_precision": 0.005494500329872309, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0007044489282665799}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_recall": 0.006910731196408219, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0008474442564134671}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeL_fmeasure": 0.0046037610582904, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0004842752495293122}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_precision": 0.006515436893618955, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0008141521585116435}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_recall": 0.008010452744131268, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0009551600048254268}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "rougeLsum_fmeasure": 0.0055130820845512825, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0005938752458158761}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "article_summary_en", "bleu": 1.2081769471696679e-09, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "2038df7b-5420-4a33-87ec-09715419deef", "prompt_jinja": "Article in English: {{source}}\n\nSummary in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 4.7758554492272945e-09}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a96171b85dc6584b4be83cf7152effc24483b2be --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_precision": 0.10569868627384524, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017140526493108679}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_recall": 0.16204648662100252, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002316216467829637}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_fmeasure": 0.1174568672178565, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0016459536455676414}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_precision": 0.013201893034513962, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005378682826493545}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_recall": 0.022027771467537875, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009738896413116423}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_fmeasure": 0.015045420297771185, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0005981449989858111}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_precision": 0.08838578365243173, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013067594648947581}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_recall": 0.1392947948040508, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019179440859143518}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_fmeasure": 0.0992022930965774, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012654116495173472}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_precision": 0.09855134328369819, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015934085607222398}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_recall": 0.15144176964309033, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002157349066143636}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_fmeasure": 0.10959697102431157, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0015286108227936896}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "bleu": 0.8117389101795618, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05120531843865198}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..40c3328ecb9d1c345022a72be49038318d4d7c4e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_precision": 0.11390300359943901, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001505310086956201}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_recall": 0.11050639157282433, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0014435125389142748}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_fmeasure": 0.098994814039191, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0011402494962994437}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_precision": 0.004517191185289906, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0002871310006425094}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_recall": 0.004113881151457014, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00027381193246220814}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_fmeasure": 0.0038137867450023814, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00023343889478032686}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_precision": 0.09172939994661446, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011916256374520841}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_recall": 0.089104978321703, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0011511611569130506}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_fmeasure": 0.07918587597477968, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008565313092324011}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_precision": 0.10993079553359293, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014392346467215847}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_recall": 0.1069392153189123, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0013956438936564995}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_fmeasure": 0.09563169367500524, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001091436945649962}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "bleu": 0.2794013007287592, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04394092663556765}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2bb831389594ca7e8f9812f21ca2dd67a2f7159f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_precision": 0.11467425239533192, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015225012916013473}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_recall": 0.11441629521647928, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0015727059489721053}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_fmeasure": 0.10072739595349496, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0011867245098453186}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_precision": 0.005508580331675803, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00035383861846697813}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_recall": 0.005934869967984835, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0004322756043539301}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_fmeasure": 0.004828784168441771, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002759061972464504}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_precision": 0.09149413336589454, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011975294685730132}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_recall": 0.09135200468914431, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0012290284607197216}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_fmeasure": 0.07966550478447607, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008671984140603575}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_precision": 0.11056182525730968, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014655410176995765}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_recall": 0.11035544182626898, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0015086333978719083}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_fmeasure": 0.09709883418158977, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0011361943688270538}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "bleu": 0.3628903862281783, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.040600834550736854}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..14f9e30d31b54cbf31a02e7641e31c6e70b08b8c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_precision": 0.09881225588094651, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017794429029784138}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_recall": 0.0961080094935916, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001760024204009069}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_fmeasure": 0.08360995103143794, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0013441180625539642}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_precision": 0.0059206327308198945, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004468897050553651}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_recall": 0.005917242814787239, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00045428975938505313}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_fmeasure": 0.00494689889012699, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00032931853157837956}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_precision": 0.07953381242832525, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001428896234358919}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_recall": 0.07718976821843865, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0013856069309638303}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_fmeasure": 0.06662277406174887, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0010213036544403373}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_precision": 0.09515792843426966, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001709487622838808}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_recall": 0.09256568091207279, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0016852915566244572}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_fmeasure": 0.08045562840916225, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0012855845245021166}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "bleu": 0.3640822400959341, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04928248150151389}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..5a83d66120b8ac2e365e299500ebc0fed4d4c816 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_precision": 0.0317245796662674, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0013705699322416266}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_recall": 0.03146018864612653, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0014391156321984263}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_fmeasure": 0.02596269332900368, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0010634101020032597}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_precision": 0.002339551167089779, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00030256564830245586}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_recall": 0.003101162831484645, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0004679085866658427}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_fmeasure": 0.0019833072972918566, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002144425508793813}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_precision": 0.026049745321603573, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011243334623461175}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_recall": 0.025594964978776304, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0011360606064423507}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_fmeasure": 0.020998319543683103, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008262281758861216}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_precision": 0.03023574490650669, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013013309198418228}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_recall": 0.029726826443738044, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0013382698786662225}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_fmeasure": 0.02460219706818639, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0009968526836547482}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "bleu": 0.022070239323623318, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.009020956658967978}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d80410636bc6c5d2f4535f02514f2a8d24e19f36 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_precision": 0.004997411592452321, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0005839652233329812}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_recall": 0.00516993867487459, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0007131741906943778}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge1_fmeasure": 0.004061499208353005, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00046516835238848473}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_precision": 0.00030964206877279654, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 8.927954397265049e-05}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_recall": 0.0005971005703343351, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00021977639166152163}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rouge2_fmeasure": 0.0002762510614131578, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 7.152448161217703e-05}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_precision": 0.004026290704976211, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00046120664542663453}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_recall": 0.0042081128532273256, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0005776147810982953}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeL_fmeasure": 0.003257613603154482, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0003601612804489262}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_precision": 0.004781410549830059, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0005638818969053312}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_recall": 0.004893422518392296, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0006832059638435896}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "rougeLsum_fmeasure": 0.0038410375028680617, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00043981063385292154}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "rephrase_en", "bleu": 1.2772835382495755e-13, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "753f0a46-aeff-4cd2-932c-8548897cebe5", "prompt_jinja": "{{source}}\n\nHow would you rephrase that briefly in English? ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 3.981569081927512e-12}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a882b758be7b38acd9d85fadaf11e749a8fbf89c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_precision": 0.05321505980023667, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0014181666167610405}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_recall": 0.07795628718339453, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0018410017875166815}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_fmeasure": 0.05817807410278456, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0013730134887578534}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_precision": 0.004212936258690241, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00028227201371374533}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_recall": 0.006550413011055106, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0005770046318012553}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_fmeasure": 0.004598565155715411, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0003111709286716547}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_precision": 0.05005075628972684, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001278959345154331}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_recall": 0.07412927953859504, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0016956652339899909}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_fmeasure": 0.05496385663485581, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012393700178193036}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_precision": 0.04982130748814443, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013143803339713488}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_recall": 0.07363722344726391, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0017324048141738725}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_fmeasure": 0.05462669247662518, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001271676260318409}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "bleu": 0.2519277717730189, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.03524949351036431}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c5555a125aeb2c5ec3f4f7b0fab5b08d98043129 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_precision": 0.11385785104351803, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0014965391184321181}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_recall": 0.10937667766926965, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0014145590881837738}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_fmeasure": 0.0987597492588469, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0011303207925802167}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_precision": 0.004457883873596226, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0002826935523898672}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_recall": 0.0040283569854367126, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0002662158979064575}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_fmeasure": 0.003733269944172192, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002255133736408092}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_precision": 0.09155580309452313, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011764557134249975}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_recall": 0.08815903146004761, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0011271831761762122}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_fmeasure": 0.07895189836522858, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008476363984155375}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_precision": 0.10994991245043519, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014301005338092242}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_recall": 0.10592427428936108, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.001368238986007311}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_fmeasure": 0.09547883528709802, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0010834332898652644}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "bleu": 0.23894215568211405, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0231127989782631}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..36fab223b2a9e990e62df6b5df4dae3b248df7e0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_precision": 0.1163150797172004, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015925911586497405}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_recall": 0.11665631687345931, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0016340035824879626}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_fmeasure": 0.10225814979631906, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0012292507820030408}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_precision": 0.006595299157223728, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005108250821972147}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_recall": 0.006811278906280594, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0005095210834151304}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_fmeasure": 0.005602755335977656, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000365207226287633}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_precision": 0.09346370560850872, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012527414348738914}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_recall": 0.09379022195144442, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0012826081895714718}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_fmeasure": 0.08152225050163284, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0009069898459798317}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_precision": 0.11220025027683658, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015289183398502308}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_recall": 0.11254662956683745, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0015531537080274286}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_fmeasure": 0.09858585234149649, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001170030683997042}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "bleu": 0.4379392770159711, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.059428018607743945}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ae8d697e1d032b9d6ccdf70da8e765a74c858b40 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_precision": 0.10060948026044556, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018664954448892226}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_recall": 0.10197302779012452, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0019812796311759295}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_fmeasure": 0.08654940806312904, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001431495451108354}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_precision": 0.007376831208587836, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005437291438342406}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_recall": 0.008673705432290764, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0007007938800809519}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_fmeasure": 0.0065193989842291565, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00042504340054855125}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_precision": 0.08088970368544203, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0014724520083722664}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_recall": 0.08233682962107754, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0015887611692809386}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_fmeasure": 0.06915495549341871, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0010949721512951217}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_precision": 0.09635575140755301, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017746806567606403}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_recall": 0.09756525164753817, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.001879769069025684}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_fmeasure": 0.082797340411407, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001354438253975997}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "bleu": 0.5442256675776663, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.037604550641844786}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e681f73e618afbf604a0abe793d4068706b3990c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_precision": 0.03285278805076312, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.00151492862638139}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_recall": 0.033499707980673206, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0015787383836412087}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_fmeasure": 0.02705120556648003, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001128461395321214}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_precision": 0.003253495732258925, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00040392310255452183}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_recall": 0.004071265417854878, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0005813660435076962}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_fmeasure": 0.0026853344180586664, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002789624736107807}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_precision": 0.027230939273538826, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001255620650530008}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_recall": 0.02759081624466607, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0012884449077523894}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_fmeasure": 0.022141442290806702, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008958829005211576}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_precision": 0.031233183019105354, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014213211972707832}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_recall": 0.0319845426682248, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.001491847145002001}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_fmeasure": 0.02576886539837896, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0010599565782314143}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "bleu": 0.027510143284592198, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.005850102428249243}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2afbcc3caa15dfc72efc8828afbda7daf3e7b54a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_precision": 0.005131645813217702, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0006494612556736446}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_recall": 0.0046603087139718904, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0005994833560269134}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge1_fmeasure": 0.004055948100688518, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00047821717141908343}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_precision": 0.0006565696469248757, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00021376994443478634}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_recall": 0.00046749083156390686, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00012176761634464935}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rouge2_fmeasure": 0.00042158314099139017, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00010671999988396933}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_precision": 0.004234119839442783, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005284078757495208}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_recall": 0.00396076135348473, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0005103337395972377}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeL_fmeasure": 0.003372046824276411, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00038942868804587514}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_precision": 0.004974502856539407, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0006280274207578934}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_recall": 0.004513499194743017, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0005832210379541333}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "rougeLsum_fmeasure": 0.0039257863548093274, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00046232884670699545}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "summarize_above_en", "bleu": 3.9529978759982985e-15, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "088288f3-7516-4cf7-9406-0e082053bf54", "prompt_jinja": "{{source}}\n\n===\n\nWrite a summary of the text above in English : ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 1.548319477203052e-13}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e15998cf1bb92bad4e243f4439336a29e7bafa30 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.1078207522843226, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001940682197702513}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.1520153396969911, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002277894036435405}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.11334607060168528, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0016396098775080439}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.011837859560447648, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005138331303314764}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.019458716329622143, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009420647807959251}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.013280003159457142, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000558295558429676}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.09180182708936059, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0016152505728822433}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.13192962900825583, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019204374301591803}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.09699392119251118, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012980799468792427}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.10116224232784549, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001831498246711715}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.14236722673055757, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021081023222958317}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.10617032427066436, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0015161029623370764}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.6707270817884038, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.046602035483089825}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..affb8d4ed60a913a0343f6c4f7ca2d7acf5ab6f9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.1160224630989691, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015635722100785284}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.11479872451661574, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0016007866744804707}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.10140750562931955, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001200027323440739}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.005941589755812423, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004274156364302611}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.006017596275684403, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00041646260466011385}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.00507966104363529, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00030717988724990536}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.09349045000409738, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012461235636124553}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.09234699285193011, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0012589640727499547}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.08108861724066418, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.000902890435608752}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.11197455431954438, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001497949074925301}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.1110141699775543, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0015424239322369367}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.09791498603078132, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001146504425053145}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.43855817321834095, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06688374272014054}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f8d1373306553a7b31f5c87f30147e09f57a0e7f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.14110589305024318, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0022270422789620343}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.1403877205314885, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002190793145077092}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.11933695488013622, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001559164548856994}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.016440629225865595, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008773719234169698}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.01682561907914257, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0008426407227716545}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.013472946625192286, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0005971595008055532}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.11303183510467564, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017832927124786565}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.11265616862637728, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0017655005819091217}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.09470570644133551, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0011669855247486087}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.13426932254715146, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0021052543187055337}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.13349014172459456, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002067397596426611}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.11342531741430635, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0014614019347966196}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.0367136986637764, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.10294385360100548}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..cacbae0f5539edaa47073d998ddc39247ad66789 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.1432248072165103, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0028194048557081534}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.1235766277421485, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002354909584881938}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.10845969305714753, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001764500717605624}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.02165017024117859, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011383917848863225}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.018904933463519274, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009796659633542278}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.015547635018168346, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006704388234796883}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.115448783961469, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0023052494207092614}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.09991818086293902, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0018968351003013303}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.08660256700931251, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001347993958631469}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.1347230613061051, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002655304240899613}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.11587053571503414, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021893808381981995}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.10174661203721236, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016381663427203297}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.0055082276927305, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07192737514794537}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ff867664a95309f4620e7937bea65b2de9377b94 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.05608048532310048, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002435498849231569}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.041593600839943914, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001788014682833587}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.03803967268390006, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0014747568915058733}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.011745234816576059, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010829411163804264}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.007380582194532306, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0007127969246877938}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.006755300956624583, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0005462948561714105}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.047091703984391005, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002065424301205954}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.034604035967383255, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0014944258543141873}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.031443909785773674, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012099672207623704}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.05323231626482197, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0023275252393686156}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.0391023340007786, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0016636743475211388}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.03593453392452451, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0013935406055845413}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.0464769949251449, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.005281612141215288}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..1d040d4b023eabec917822f21524348e3d89e69f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.009319821178210992, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0010269796471685194}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.007261443669465562, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0009201674527650682}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.006408772411533697, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006726664225328778}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.0015883326473273408, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0003471561820758166}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.0016746964377212603, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00043827050828643875}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.001215199948152673, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00024366601487357684}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.007922705066461089, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0008728161809959782}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.006196890284199744, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.000796669253101562}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.005446190005924919, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0005737856458351668}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.008783315274046653, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0009687512562761863}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.006837799638085168, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0008734893361383668}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.006002979726182862, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0006246362092905004}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 7.71421931319727e-14, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 4.575898076497286e-13}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..fb51b7f1a86ffc9e37b49140da14cdeb088d0ac2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_precision": 0.1467073059254317, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003923847788182457}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_recall": 0.1488423584822216, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002514278160277046}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_fmeasure": 0.11287104782454531, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0018302548422649888}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_precision": 0.015139213553420103, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0006017762732827434}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_recall": 0.023991338309341914, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0010741770192485198}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_fmeasure": 0.0168939526317488, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006560231719498498}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_precision": 0.12846108969943054, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0037967129632843506}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_recall": 0.12514947700874288, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002011926521503057}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_fmeasure": 0.09354722719833262, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001367594008196884}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_precision": 0.13919269715957514, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003880077948366859}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_recall": 0.13851578235021383, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0023319716005974654}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_fmeasure": 0.10483417861156145, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016823495491907201}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "bleu": 0.8049467835361911, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06125790470590714}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..0443a9e5f5ea9cf03a68d3bcd002e5b91a720270 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_precision": 0.11672921172744681, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015455078946896611}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_recall": 0.12404651186718361, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001833482506124768}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_fmeasure": 0.10581662192060133, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001297467104327135}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_precision": 0.00662318107917187, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00038908144611155763}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_recall": 0.008569619519959264, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0005860808060358155}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_fmeasure": 0.006578200350543033, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0004020452136350789}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_precision": 0.09258137259929677, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011789964767188995}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_recall": 0.09781932700181184, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0013635799564556685}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_fmeasure": 0.08315064354847855, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0009263412660918235}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_precision": 0.11236796963847627, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014661420025751913}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_recall": 0.11962539469182883, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0017515297053630175}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_fmeasure": 0.10191075189261449, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0012281012231510622}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "bleu": 0.6042770786450469, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06784193000730189}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..cfe11c95134008d4f5d550a0c78ac9f704b4b84e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_precision": 0.11791706075978581, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015994717296165192}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_recall": 0.14298806278491627, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0020625427368130608}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_fmeasure": 0.11408900626000608, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0014182183684096998}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_precision": 0.008285813515207935, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004549347251757663}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_recall": 0.012254279196802272, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0007733247902712675}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_fmeasure": 0.008686912843235644, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00045294754346949324}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_precision": 0.09043062219460844, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0011743927829203635}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_recall": 0.10998900310161605, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0015428002199032057}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_fmeasure": 0.0867863689660142, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0009676979999670107}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_precision": 0.11235660105208539, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001507091449296961}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_recall": 0.1359188111061881, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0019151506035573415}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_fmeasure": 0.1085601417082136, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0013181344740805481}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "bleu": 0.6359039546247384, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05332890289165686}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..0ad4f1b39cba0e4464225cd60bae24a1ca5008de --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_precision": 0.09005735863253914, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017410925572476383}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_recall": 0.11209657560256954, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002246234879953545}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_fmeasure": 0.0863434945247995, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0015282100730080173}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_precision": 0.006965462874923481, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004357269928233993}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_recall": 0.01068806664642742, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0007581392108308288}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_fmeasure": 0.007238486310418053, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00042895291336820845}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_precision": 0.06963288035102946, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013235845589289316}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_recall": 0.08642316047519256, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0017071161351831217}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_fmeasure": 0.06590039763154197, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0010964007554027833}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_precision": 0.08570933352018638, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001644764365928756}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_recall": 0.10632118573218488, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002114071365640021}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_fmeasure": 0.08200533326129804, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0014384128001919997}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "bleu": 0.5690290357096291, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08303885182927963}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c6a8f399f521c71b0c1de1be8abba6c844562b35 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_precision": 0.02299224348433701, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0011412033083596786}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_recall": 0.030086106435386208, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001556085408646244}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_fmeasure": 0.021738632248596658, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0010230448733526455}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_precision": 0.0017495363473227336, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00020151602411722723}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_recall": 0.0032970556699345034, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0004918025374367564}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_fmeasure": 0.001875948079941924, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000219572547682823}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_precision": 0.01828959837223259, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0009017986426573455}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_recall": 0.024055207310948443, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0012481605588282325}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_fmeasure": 0.01708346323437329, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0007728353496458206}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_precision": 0.021695271758735132, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0010708297762772132}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_recall": 0.028324718060384762, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.001443357150753234}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_fmeasure": 0.02048581320979614, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0009585758119225723}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "bleu": 0.016816379280954568, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0028919321680318318}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c43809b42db03c9e486dec09322864a07757fc03 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_precision": 0.0023192080637707735, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.00038854174236947536}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_recall": 0.0037156411516436165, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0006659054396004237}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge1_fmeasure": 0.0023847991624654733, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.000384610434523063}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_precision": 0.00024483684853279374, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 7.040995395638042e-05}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_recall": 0.0005891611955524744, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00018205158176419917}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rouge2_fmeasure": 0.0003122235342379389, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 9.229879998061021e-05}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_precision": 0.0018119271192860117, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0002971679095161747}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_recall": 0.0028628954473527285, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0005077613704836201}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeL_fmeasure": 0.001821148625234418, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0002799930215985291}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_precision": 0.002232415013733976, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.000374058105161406}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_recall": 0.0035504517322428614, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0006368246151758458}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "rougeLsum_fmeasure": 0.0022835778404728443, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00036781738986975464}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "write_abstract_en", "bleu": 1.1597815660645416e-20, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "dff7b314-7385-4855-bb90-253073a34fde", "prompt_jinja": "First, read the English article below.\n\n{{source}} \n\nNow, please write a short abstract for it in English. ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 6.856426087822371e-20}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..4951b787257aaac48cfe72fa841228f5c21fca1d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc": 0.329, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014865395385928376}, {"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc_norm": 0.333, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014910846164229856}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..920a7ccb0146a794d4b0e0aedb72cccd5e5c8fdf --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc": 0.334, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01492201952373296}, {"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc_norm": 0.328, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014853842487270334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e74ae756de5482fa32a4ee85db5c383ffcdc3d8b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc": 0.363, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015213890444671288}, {"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc_norm": 0.354, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015129868238451772}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3ffe1ff8ae73d00223fbecb527c949995bc2f0de --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc": 0.355, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015139491543780529}, {"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc_norm": 0.339, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014976758771620335}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..fa397e9c73da5b16f8a50152cdb41164210dde22 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc": 0.348, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01507060460376841}, {"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc_norm": 0.354, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015129868238451773}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..21ac5debac8d0c392f82623802ceaec4c4ca43f9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_GPT-3-style_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc": 0.352, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015110404505648658}, {"task_name": "anli_r1", "prompt_name": "GPT-3 style", "acc_norm": 0.355, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015139491543780529}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..6f982821df0ef0c936747f6bcf3cb1f4487a31c2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc": 0.331, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01488827258820393}, {"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc_norm": 0.32, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01475865230357488}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..433d83c3ee46c84f04c40ff2313b6a26155f59f3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc": 0.333, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014910846164229863}, {"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc_norm": 0.333, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014910846164229863}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..65ef3f61dfecfb6e41fda4ef18c589ab0cc9864e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc": 0.339, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01497675877162034}, {"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc_norm": 0.333, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014910846164229864}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d8adff4ec2282e0926a4ace1d69a3ad1fedf6536 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc": 0.329, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014865395385928367}, {"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc_norm": 0.332, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014899597242811485}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..6cc01a7f0fa239a16105a148944d5e3c86bc24a8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc": 0.327, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014842213153411244}, {"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc_norm": 0.325, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014818724459095524}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a373289dd8d6cd51ea3cfa049d9781c5ae6e3cd5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc": 0.308, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014606483127342763}, {"task_name": "anli_r1", "prompt_name": "MNLI crowdsource", "acc_norm": 0.302, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01452608023545955}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..80ff20b8d0111d35eb926b8a31d7c7615e70f4b1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "can we infer", "acc": 0.336, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014944140233795027}, {"task_name": "anli_r1", "prompt_name": "can we infer", "acc_norm": 0.346, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015050266127564438}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..3e9cf45141d77f107e561e9a4c00fd55d646931e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "can we infer", "acc": 0.331, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014888272588203933}, {"task_name": "anli_r1", "prompt_name": "can we infer", "acc_norm": 0.338, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01496596071022448}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..04d21fdb04db51b388ce5ffcc6469cfe09a50686 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "can we infer", "acc": 0.353, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0151201726054837}, {"task_name": "anli_r1", "prompt_name": "can we infer", "acc_norm": 0.354, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015129868238451772}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..13c48656d5c3e30e1bdae03c4189cdb6847d8f44 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "can we infer", "acc": 0.35, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015090650341444236}, {"task_name": "anli_r1", "prompt_name": "can we infer", "acc_norm": 0.335, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014933117490932575}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..05ed3bb0d43c4565f135ff536ba9422ca8b539fc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "can we infer", "acc": 0.335, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014933117490932577}, {"task_name": "anli_r1", "prompt_name": "can we infer", "acc_norm": 0.344, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015029633724408947}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..527100d6132afe8cff94fe28e445264dd57af1ff --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_can-we-infer_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "can we infer", "acc": 0.342, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015008706182121728}, {"task_name": "anli_r1", "prompt_name": "can we infer", "acc_norm": 0.334, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014922019523732958}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..3adebb2d5f972e247a50f44ea399fcc1d0566767 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc": 0.324, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014806864733738863}, {"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.332, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014899597242811475}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..5c11e9cc521c05d87df6fc70b4e44a9ef1db5664 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc": 0.333, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014910846164229863}, {"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.333, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014910846164229863}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a1c76983385e8ac6a3d9e7c3ccec327c64d3333c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc": 0.348, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01507060460376841}, {"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.348, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01507060460376841}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..477a4b9418c2662af08de34d62b14e17fbc5fb75 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc": 0.35, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015090650341444233}, {"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.35, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015090650341444233}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..50d7289b1e13dee38d3e334e5fa4bd4e7126bea8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc": 0.325, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014818724459095522}, {"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.335, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014933117490932579}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2d176c85ba64604b6ae0a635a967bf084d573da4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc": 0.328, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014853842487270334}, {"task_name": "anli_r1", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.327, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01484221315341124}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..16f2f76b897463f1cbc9fc37ee156f0c38e0298d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "justified in saying", "acc": 0.333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014910846164229875}, {"task_name": "anli_r1", "prompt_name": "justified in saying", "acc_norm": 0.355, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01513949154378053}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..69d357636eb142468486e40cd7bbbf70bcd4f0f1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "justified in saying", "acc": 0.332, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014899597242811485}, {"task_name": "anli_r1", "prompt_name": "justified in saying", "acc_norm": 0.336, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014944140233795023}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..81fc496d318999b22746aba5ce931389c56f7667 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "justified in saying", "acc": 0.353, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015120172605483703}, {"task_name": "anli_r1", "prompt_name": "justified in saying", "acc_norm": 0.354, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015129868238451772}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..baf203fd85f8f686f4e1038ef3b3b3e835975ac7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "justified in saying", "acc": 0.346, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015050266127564433}, {"task_name": "anli_r1", "prompt_name": "justified in saying", "acc_norm": 0.331, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014888272588203931}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b6073ac43ec92ae947c3e779e60139f50bfaa28c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "justified in saying", "acc": 0.345, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015039986742055235}, {"task_name": "anli_r1", "prompt_name": "justified in saying", "acc_norm": 0.355, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01513949154378053}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..284cb8295b0407815e1a4b7a8973b2e779b1a166 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r1_justified-in-saying_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r1", "prompt_name": "justified in saying", "acc": 0.344, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015029633724408947}, {"task_name": "anli_r1", "prompt_name": "justified in saying", "acc_norm": 0.343, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 1, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015019206922356953}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..f4aebbe06be176ff7229847af79a1f1f512b28bc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc": 0.32, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01475865230357489}, {"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc_norm": 0.342, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015008706182121734}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..2aabfc1d3d6bef2124a34529b20d3fbb13229fcd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc": 0.321, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014770821817934647}, {"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc_norm": 0.315, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014696631960792506}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..fbcf155b35adcf2f6afc3853ffa84d5c3ad872a1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc": 0.33, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01487687202745673}, {"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc_norm": 0.326, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014830507204541028}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..92609a42a9b1eac2a7e86a7cfc32c1749afba1ce --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc": 0.321, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014770821817934649}, {"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc_norm": 0.329, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014865395385928369}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..9ca7a676792c293255be4d75f72dcf41693971ff --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc": 0.327, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014842213153411239}, {"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc_norm": 0.318, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014734079309311901}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2f4209354043b0486e45f76da125ea2b1aa52cbb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_GPT-3-style_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc": 0.337, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014955087918653591}, {"task_name": "anli_r2", "prompt_name": "GPT-3 style", "acc_norm": 0.329, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014865395385928373}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..cd0fbaca19f20a2fbd53f54d8688bcabb151df68 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc": 0.339, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014976758771620342}, {"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc_norm": 0.323, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014794927843348642}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..e72c668d9c7f2c5b572b14c1cdd4c76542a67135 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc": 0.315, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014696631960792506}, {"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc_norm": 0.315, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014696631960792506}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0b8ea14c196f7e0661eb665c19037e9e53275847 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc": 0.327, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014842213153411237}, {"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc_norm": 0.327, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014842213153411237}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..b8e4d7db83c9666876c10b93c0da10a94702f282 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc": 0.329, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014865395385928367}, {"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc_norm": 0.327, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014842213153411242}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..d92779e053859e05380783bc2d26e41af6cfbf85 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc": 0.305, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01456664639466438}, {"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc_norm": 0.311, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014645596385722692}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..5aec2cbb4e4af767ff7d1efc4bfe7dd9a33b25cf --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc": 0.313, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014671272822977892}, {"task_name": "anli_r2", "prompt_name": "MNLI crowdsource", "acc_norm": 0.317, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014721675438880233}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..3d06b5f637a3466318c8fbfef38b461b0770c1fd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "can we infer", "acc": 0.33, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014876872027456729}, {"task_name": "anli_r2", "prompt_name": "can we infer", "acc_norm": 0.336, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014944140233795023}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..aab7dacae68bc915a942537f9ccbf305f4d0fc81 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "can we infer", "acc": 0.325, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014818724459095524}, {"task_name": "anli_r2", "prompt_name": "can we infer", "acc_norm": 0.32, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014758652303574886}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..707d73642b9279c8cac6eeb54b912fe673d89986 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "can we infer", "acc": 0.326, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014830507204541031}, {"task_name": "anli_r2", "prompt_name": "can we infer", "acc_norm": 0.333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014910846164229873}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8b0d435f85a484c6ddee7dbd4438e379ed1904f3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "can we infer", "acc": 0.312, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014658474370509014}, {"task_name": "anli_r2", "prompt_name": "can we infer", "acc_norm": 0.329, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01486539538592837}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..68a3459b07dea082e985a76047c997c6fa2603f6 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "can we infer", "acc": 0.316, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014709193056057134}, {"task_name": "anli_r2", "prompt_name": "can we infer", "acc_norm": 0.318, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014734079309311901}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..70b3d4307f279ae44e29bb987009cf7372abe9ff --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_can-we-infer_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "can we infer", "acc": 0.326, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014830507204541033}, {"task_name": "anli_r2", "prompt_name": "can we infer", "acc_norm": 0.334, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014922019523732954}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a7daa45ac95616cc14a86222ee56255ac1b17675 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc": 0.334, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01492201952373296}, {"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.332, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01489959724281147}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..476d1c23ac77f768dcafb9a5d0c3c554205a91d5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc": 0.315, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014696631960792506}, {"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.315, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014696631960792506}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..9483a2199ae7c0b4d6c697ac43d35b59e1354a4c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc": 0.321, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014770821817934649}, {"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.319, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014746404865473477}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..75b2660c77a95d481d8764da01264d686650cde9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc": 0.296, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01444273494157502}, {"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.297, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.0144568322948011}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..92042b894ff39ca9f2dff79902702a195fe60e1c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc": 0.316, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01470919305605712}, {"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.311, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014645596385722694}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..093353b1db0c2a3a186255f7e9271fe24d28d6d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc": 0.325, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014818724459095524}, {"task_name": "anli_r2", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.328, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014853842487270334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..8e9f635768da364975996c74037abe7b31ac8680 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "justified in saying", "acc": 0.333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014910846164229873}, {"task_name": "anli_r2", "prompt_name": "justified in saying", "acc_norm": 0.338, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01496596071022447}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..51059449927dc20322172814f624da490ea27a10 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "justified in saying", "acc": 0.324, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01480686473373886}, {"task_name": "anli_r2", "prompt_name": "justified in saying", "acc_norm": 0.321, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014770821817934647}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e81ece5fda9f1ea524fe12db54f1f3adbf352537 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "justified in saying", "acc": 0.328, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014853842487270334}, {"task_name": "anli_r2", "prompt_name": "justified in saying", "acc_norm": 0.331, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014888272588203928}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..cfdc68851320ad3c92480784b5f108d0c4b7c88b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "justified in saying", "acc": 0.318, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014734079309311901}, {"task_name": "anli_r2", "prompt_name": "justified in saying", "acc_norm": 0.318, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014734079309311901}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3a8d2a5ea5eef6773564efa292a4531e4b085cc2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "justified in saying", "acc": 0.314, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014683991951087978}, {"task_name": "anli_r2", "prompt_name": "justified in saying", "acc_norm": 0.328, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01485384248727033}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..3e1f5e0d9b5135ecae900db18f96e3151cb1a7e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r2_justified-in-saying_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r2", "prompt_name": "justified in saying", "acc": 0.329, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014865395385928369}, {"task_name": "anli_r2", "prompt_name": "justified in saying", "acc_norm": 0.338, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 2, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014965960710224468}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..cccafe8abeb7a98e56b1f8550b49b2bd342bc04f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc": 0.30416666666666664, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013286140243317441}, {"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc_norm": 0.3416666666666667, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013696658778002519}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c7763d68824dbe3cdc459e5d92da195a0d9b4fb4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc": 0.3433333333333333, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01371263383046586}, {"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc_norm": 0.3375, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013655897185463657}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..93fd1774674723ba777b405c0e4476fd13432c10 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc": 0.335, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013630871843821465}, {"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc_norm": 0.3383333333333333, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013664144006618261}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..918878f5f2ca78cc796b0a99df558a5c8d6da847 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc": 0.3541666666666667, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013811933499570954}, {"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc_norm": 0.35583333333333333, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01382651874849331}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b72048a1ac235eaa053ea833aaea11b0f807fb14 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc": 0.34833333333333333, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013759437498874072}, {"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc_norm": 0.32416666666666666, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013517438120881617}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..63730acda126bbaa1ed48500cbb1b59fe0bf2df7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_GPT-3-style_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc": 0.32916666666666666, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013570806258433628}, {"task_name": "anli_r3", "prompt_name": "GPT-3 style", "acc_norm": 0.3225, "fixed_answer_choice_list": ["True", "Neither", "False"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "620aa3fc-d5eb-46f5-a1ee-4c754527aa97", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013499258621103247}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e752b00c3feb269a0930f6e665dc8ecd9d80a2f7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc": 0.3358333333333333, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013639261190932873}, {"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc_norm": 0.33416666666666667, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01362243481313678}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f0e6c9b27275ab6e8f149f6549203c7f47bffe33 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc": 0.33666666666666667, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013647602942406393}, {"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc_norm": 0.33666666666666667, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013647602942406393}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..591a3204bbd409d21a64ba184caa5a2bf9a063b4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc": 0.30833333333333335, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013336721143136469}, {"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc_norm": 0.3075, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013326707242912048}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..c11a0b874ba0d86288abfadbc6d7c1981939a7cf --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc": 0.3308333333333333, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013588208070708999}, {"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc_norm": 0.32416666666666666, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013517438120881636}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..4d7dd2ecf4f91d1aba4698853980b9d5cf9e7e7d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc": 0.32916666666666666, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013570806258433628}, {"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc_norm": 0.3283333333333333, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013562032919529019}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..76d6e2208cd25873a0e2331678e1e491b281944a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc": 0.29833333333333334, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013213160837301237}, {"task_name": "anli_r3", "prompt_name": "MNLI crowdsource", "acc_norm": 0.30833333333333335, "fixed_answer_choice_list": ["Correct", "Inconclusive", "Incorrect"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "0cc3ae39-3997-4686-8c93-5d51457efa1f", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013336721143136467}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..185167607ca2161c329556e8575647dae3f16a2a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "can we infer", "acc": 0.3233333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013508372867300217}, {"task_name": "anli_r3", "prompt_name": "can we infer", "acc_norm": 0.3333333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013613950010225613}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f50cf7aabba048577bf2ddc5d6a3db4494429b34 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "can we infer", "acc": 0.345, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013728421539454876}, {"task_name": "anli_r3", "prompt_name": "can we infer", "acc_norm": 0.3408333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013688600793296934}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d05d6e660087ce0bb1909fd419aa4adde411edb2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "can we infer", "acc": 0.3275, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013553211167251953}, {"task_name": "anli_r3", "prompt_name": "can we infer", "acc_norm": 0.32666666666666666, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013544340907003665}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..aeef03fad5c66e6ceb22a0eafbf97ef547dd5334 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "can we infer", "acc": 0.3433333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01371263383046586}, {"task_name": "anli_r3", "prompt_name": "can we infer", "acc_norm": 0.3525, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01379716491891836}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..5834278675eb76057770c8b84681adb3486b1f38 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "can we infer", "acc": 0.3466666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013744022550571942}, {"task_name": "anli_r3", "prompt_name": "can we infer", "acc_norm": 0.33916666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013672343491681808}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4d4ea783a46585a2b5d68db1be00b9ef03e64723 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_can-we-infer_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "can we infer", "acc": 0.3308333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013588208070708992}, {"task_name": "anli_r3", "prompt_name": "can we infer", "acc_norm": 0.3258333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "c4ed37ae-d7d7-4197-a725-ef2152fa3b1f", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013535422043417466}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..235336d331f0ff9181802bc4f740b4ffd735f1e7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc": 0.32916666666666666, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013570806258433628}, {"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.33, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013579531277800918}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..bbd456cc9ecb93bbf455c93315a70ae492be8c86 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc": 0.33666666666666667, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013647602942406393}, {"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.33666666666666667, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013647602942406393}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..9e63d6bdedee74d78bf9828a440682648c0c3b53 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc": 0.31333333333333335, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013395739415639082}, {"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.31, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01335659633120026}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a1ac18851148c39cf25609ecea16e1faee5f23d4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc": 0.32, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013471620929769142}, {"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.32, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01347162092976914}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..fd82b785c908f977ab403f3561a6e0401e9a9b86 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc": 0.3175, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013443538681348052}, {"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.31833333333333336, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.0134529489969963}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..7537869876d77c6a314c1006a1801be983aeb2fd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc": 0.31, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013356596331200258}, {"task_name": "anli_r3", "prompt_name": "guaranteed/possible/impossible", "acc_norm": 0.31166666666666665, "fixed_answer_choice_list": ["Guaranteed", "Possible", "Impossible"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "ca24b93a-6265-462f-b140-e329c03d94fa", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {{ answer_choices[label] }}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.0133762687909821}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..9ca574394b9f3f33674268289cf01622189c1616 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "justified in saying", "acc": 0.33166666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013596836729485159}, {"task_name": "anli_r3", "prompt_name": "justified in saying", "acc_norm": 0.33416666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01362243481313677}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d943481cf214f16088990f89d99cb18bae169f1d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "justified in saying", "acc": 0.355, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013819249004047296}, {"task_name": "anli_r3", "prompt_name": "justified in saying", "acc_norm": 0.33916666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013672343491681819}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..146be1f2293e740cb960ff4c419c2a3b17e99f63 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "justified in saying", "acc": 0.33166666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01359683672948517}, {"task_name": "anli_r3", "prompt_name": "justified in saying", "acc_norm": 0.3233333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01350837286730022}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..37a0077ee19fec48371375371ccf12ec751056e9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "justified in saying", "acc": 0.345, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013728421539454878}, {"task_name": "anli_r3", "prompt_name": "justified in saying", "acc_norm": 0.3541666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013811933499570956}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bd87dcfb0e9fe9596fb9dfe61fe63e3513661760 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "justified in saying", "acc": 0.3408333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013688600793296939}, {"task_name": "anli_r3", "prompt_name": "justified in saying", "acc_norm": 0.33416666666666667, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013622434813136765}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d8823a22ce1b1598ac988492ddeee6feb25c75ff --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_anli_r3_justified-in-saying_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "anli_r3", "prompt_name": "justified in saying", "acc": 0.32666666666666666, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.013544340907003663}, {"task_name": "anli_r3", "prompt_name": "justified in saying", "acc_norm": 0.3233333333333333, "fixed_answer_choice_list": ["Yes", "Maybe", "No"], "dataset_path": "anli", "dataset_name": null, "subset": 3, "prompt_id": "a850110d-f1a3-49b4-949a-d3bfe9f81344", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {{ answer_choices[label] }} ", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.013508372867300231}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e31495e53c0360eeaeb441b679ebdf9abadaf2f0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.2175767918088737, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0120572620209725}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.2175767918088737, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.0120572620209725}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_1.json new file mode 100644 index 0000000000000000000000000000000000000000..ae730f86030d004a36d2205b475e97354d2573d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.23378839590443687, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012368225378507148}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.23378839590443687, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012368225378507148}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_2.json new file mode 100644 index 0000000000000000000000000000000000000000..c18fabf4c9818385e8a793bb41201d0a66d13021 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.23208191126279865, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012336718284948854}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.23208191126279865, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012336718284948854}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_3.json new file mode 100644 index 0000000000000000000000000000000000000000..1f7d17eae2f463afe746d440be4143cebc1ee8f7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.24146757679180889, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012506564839739429}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.24146757679180889, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012506564839739429}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e2c7476c33c7ef4e7d78ec36f26da90fba73ecbb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.24146757679180889, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012506564839739429}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.24146757679180889, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012506564839739429}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_5.json new file mode 100644 index 0000000000000000000000000000000000000000..1911aaeccf81cdd63284fe5579d45361fedb0c2b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_heres_a_problem_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.23378839590443687, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012368225378507144}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.23378839590443687, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "540ebc31-2ea6-4feb-a6fd-67b6e71cf20a", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012368225378507144}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.json new file mode 100644 index 0000000000000000000000000000000000000000..f4d12c4b04cf50d7f6d49450d33d1ec1fd7590de --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.2158703071672355, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012022975360030675}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2696245733788396, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012968040686869157}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.json new file mode 100644 index 0000000000000000000000000000000000000000..70c79f07cfac93d348b22746eff5304bf5ca935c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.2235494880546075, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012174896631202605}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.27303754266211605, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01301933276263573}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.json new file mode 100644 index 0000000000000000000000000000000000000000..cd581056379117877e1e80144a9aac71a540c9c8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.2167235494880546, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012040156713481189}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.26621160409556316, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012915774781523216}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.json new file mode 100644 index 0000000000000000000000000000000000000000..71e48c96126e044790538ecef241b8eaa4175250 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.2295221843003413, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012288926760890788}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2713310580204778, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012993807727545784}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.json new file mode 100644 index 0000000000000000000000000000000000000000..9999956de87a633a005bd25558cdc7f76ac573dc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.23037542662116042, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01230492841874761}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2713310580204778, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012993807727545784}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.json new file mode 100644 index 0000000000000000000000000000000000000000..ea72f7c019141ab89408f2d9ae26e6f642174eee --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.22610921501706485, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01222420209706329}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2627986348122867, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ff84886-9d5f-40d1-80d7-2a39b7c16ec6", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012862523175351331}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c511dcd04a09717487aad06c2e2e717df658ffc4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.22013651877133106, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01210812488346098}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.2696245733788396, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012968040686869166}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b9fb40de9df73378f5f279d6d5f1e063080787c8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.22866894197952217, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01227285358254081}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.25426621160409557, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012724999945157744}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6ffe043310d52c0e10346d719b6be736c7533656 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.2098976109215017, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011900548748047433}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.24914675767918087, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01263940711192643}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_3.json new file mode 100644 index 0000000000000000000000000000000000000000..23cc2928a9874dcbda968aac2a9b2dbfe8a4b9d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.21331058020477817, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011970971742326334}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.24658703071672355, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01259572626879013}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3fa2494bc340317b52231675d144425d31009e9c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.21331058020477817, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011970971742326334}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.25170648464163825, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012682496334042965}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_5.json new file mode 100644 index 0000000000000000000000000000000000000000..08c44f52336025bb4af57d1e1cc65edf88fa7d36 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_multiple_choice_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.21331058020477817, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011970971742326334}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.24658703071672355, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "ced2b33b-b590-4522-b041-51d7dd669561", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012595726268790132}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.json new file mode 100644 index 0000000000000000000000000000000000000000..5aec0df2f28c8fe87e7489cffc8b19afbd53196a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.22013651877133106, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012108124883460976}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.22013651877133106, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012108124883460976}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d2d398b49e3f5d1d43b8c77a1057d39bd1b48907 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.2295221843003413, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012288926760890795}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.2295221843003413, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012288926760890795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d8ad57beb6430bf63fc9a80dedaf26f082596922 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.22440273037542663, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012191404938603836}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.22440273037542663, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012191404938603836}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9265261d321dcf27a8dcfdafd90040220535ef28 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.23720136518771331, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012430399829260846}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.23720136518771331, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012430399829260846}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.json new file mode 100644 index 0000000000000000000000000000000000000000..68c6f84aa73984f423f479e3dbd23f497cb4e9c9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.24573378839590443, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012581033453730106}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.24573378839590443, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012581033453730106}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4051f751a3aa8a0c074fb4fd6b970a83b3a64051 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.22866894197952217, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012272853582540806}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.22866894197952217, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "e371fc1a-8edb-477b-b345-9d73e97ffade", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012272853582540806}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..3da474b2e780a789db48f1f9f2805a02708b811b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.20648464163822525, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011828865619002316}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.26109215017064846, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012835523909473845}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d9857a9b66939d1ede4897e906d9c03aa006d8d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2175767918088737, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012057262020972504}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.25426621160409557, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012724999945157743}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e1a9cee8232e8527be7e9c93b83641f2bc9f6dd9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2098976109215017, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011900548748047449}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.26621160409556316, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012915774781523219}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3d8e53b2ef4739bafbcc882a91ee39d06fba4717 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.23037542662116042, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01230492841874761}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.26706484641638223, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012928933196496342}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ec2784efefdcb2af0efb30dc402eb177129dac49 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2150170648464164, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012005717634133616}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.2525597269624573, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01269672898020771}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..edc2f9a5c7a245984f3eea791ad06542f8c688d7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_challenge_qa_options_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.22184300341296928, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.012141659068147879}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.25853242320819114, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Challenge", "subset": null, "prompt_id": "5ec2b8ca-e4c0-444e-b097-89ccce811550", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.012794553754288673}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_0.json new file mode 100644 index 0000000000000000000000000000000000000000..229431614deec4750d883f250a05393144949f28 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.24452861952861954, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00881946110682261}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.24452861952861954, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00881946110682261}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c905a40a15eba4e83a6d0ccab1c2fb856f156e56 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.23779461279461278, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008735850753507994}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.23779461279461278, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008735850753507994}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_2.json new file mode 100644 index 0000000000000000000000000000000000000000..56ea5d2547529da3d8d5419bfd0002356356914a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.2588383838383838, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008987501845758049}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.2588383838383838, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008987501845758049}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_3.json new file mode 100644 index 0000000000000000000000000000000000000000..54cd9c40b67525a6c1eb6097710939e6ab323d13 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.25841750841750843, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008982741341291298}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.25841750841750843, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008982741341291298}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b8db3858c95543137c9cdd9d92df3ab75e0cf849 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.25336700336700335, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008924765424529264}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.25336700336700335, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008924765424529264}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_5.json new file mode 100644 index 0000000000000000000000000000000000000000..8045c5a22929ddbb5f35611ce337e01d7be6233d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_heres_a_problem_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc": 0.25715488215488214, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008968394768971991}, {"task_name": "arc_easy", "prompt_name": "heres_a_problem", "acc_norm": 0.25715488215488214, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "d90da519-0e2c-4f9b-a546-7cba82824eb2", "prompt_jinja": "Here's a problem to solve: {{question}}\n\nAmong the 4 following options, which is the correct answer?\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n {% endfor %}|||{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008968394768971991}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_0.json new file mode 100644 index 0000000000000000000000000000000000000000..cd255c834326f6107756fa8747ac6f56a3c725d8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.29503367003367004, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009358110551087425}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2836700336700337, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009249781691140749}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_1.json new file mode 100644 index 0000000000000000000000000000000000000000..37668a0553a67fcb55c26211ac2192019346d1d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.281986531986532, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009233124071053648}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.27441077441077444, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009156177122244527}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f0759372b1fefd7423ab31774db7bd2618e8d3f5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.27904040404040403, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009203588704032635}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2748316498316498, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009160538115254954}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_3.json new file mode 100644 index 0000000000000000000000000000000000000000..1da5e0cef1b6df0f3441f44cdd790176d475fe01 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.2803030303030303, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009216306864088033}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.27314814814814814, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009143032718360347}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_4.json new file mode 100644 index 0000000000000000000000000000000000000000..7d4e1ae38585637578aa30c00188d891a220a302 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.273989898989899, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009151805901544022}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.26725589225589225, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009080463246017469}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4d90e18fed2c6b1f5f05623dfe8101f2ebb3a5f8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_i_am_hesitating_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc": 0.2769360269360269, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009182190173795889}, {"task_name": "arc_easy", "prompt_name": "i_am_hesitating", "acc_norm": 0.2680976430976431, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "4fb13ac1-f770-45ea-b5d5-91ac50b0d609", "prompt_jinja": "I am hesitating between 4 options to answer the following question, which option should I choose?\nQuestion: {{question}}\nPossibilities:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00908952657821369}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_0.json new file mode 100644 index 0000000000000000000000000000000000000000..da927d8022964cceac7fb894f1e7bcc060840fe8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.29124579124579125, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009322788837938871}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.2676767676767677, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00908500014709935}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_1.json new file mode 100644 index 0000000000000000000000000000000000000000..2227de1b645e47e75e9e9fd1b82b4563204fe0e7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.2857744107744108, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00927038060698121}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.2807239057239057, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009220526174711353}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_2.json new file mode 100644 index 0000000000000000000000000000000000000000..ba5777f143ac47c7a3810539d17c48f0e44feafe --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.2895622895622896, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009306838912173909}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.28619528619528617, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009274470774627732}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_3.json new file mode 100644 index 0000000000000000000000000000000000000000..fc60828c879b340519e001490018a38ad31620be --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.27735690235690236, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009186490105111902}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.2962962962962963, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009369711585684304}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_4.json new file mode 100644 index 0000000000000000000000000000000000000000..cd4e9d057e3f20b76d4b83d3702540d44d449164 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.2781986531986532, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009195059601583901}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.2845117845117845, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00925805092561882}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d8aa85400310c512dbdb276eb19cb3884f22e682 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_multiple_choice_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc": 0.2735690235690236, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009147424438490745}, {"task_name": "arc_easy", "prompt_name": "multiple_choice", "acc_norm": 0.2878787878787879, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "8c689423-880d-402b-8c7d-a1a98c7589e8", "prompt_jinja": "I gave my students this multiple choice question: {{question}}\n\nOnly one answer is correct among these 4 choices:\n- {{answer_choices | join(\"\\n- \")}}\n\nCould you tell me which one is correct?|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009290733161670155}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.json new file mode 100644 index 0000000000000000000000000000000000000000..71732259035dd09d53fa70b69339f7492285c91e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.24873737373737373, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008870224411653796}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.24873737373737373, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008870224411653796}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.json new file mode 100644 index 0000000000000000000000000000000000000000..8814ceab7e88217ad286554b93e78de3037cd0b7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.2398989898989899, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008762298774190588}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.2398989898989899, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008762298774190588}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.json new file mode 100644 index 0000000000000000000000000000000000000000..85dfa515c4cd1db2a1565f4300ff06f9d41bc9b4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.2596801346801347, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008996990428562215}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.2596801346801347, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008996990428562215}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.json new file mode 100644 index 0000000000000000000000000000000000000000..db72640d802e63bf38cbdb31427aa732d10aac7b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.2537878787878788, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00892965706580829}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.2537878787878788, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00892965706580829}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.json new file mode 100644 index 0000000000000000000000000000000000000000..7770f07ddea8227c58d8c93fd5cfdbcb8dab17eb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.2542087542087542, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008934537681141544}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.2542087542087542, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008934537681141544}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.json new file mode 100644 index 0000000000000000000000000000000000000000..220ffff9eb98de69ff71fee4af1e2a45db171da9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc": 0.25925925925925924, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008992251535805518}, {"task_name": "arc_easy", "prompt_name": "pick_the_most_correct_option", "acc_norm": 0.25925925925925924, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "033498ca-3d9a-47e3-b631-d881ab53b5ad", "prompt_jinja": "Pick the most correct option to answer the following question.\n\n{{question}}\n\nOptions:\n{% for letter, t in zip(answer_choices, choices.text) %}\n- {{letter}}: {{t}}\n{% endfor %} |||\n{{answerKey}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008992251535805518}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..358fb8a4261f5ab297e65f6757e8f10f3888b7cb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.3005050505050505, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009407763090599318}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.2760942760942761, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00917355987383526}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..fca4bfd8056b8061d689027ce64f2df11414e939 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.29503367003367004, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009358110551087425}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.28114478114478114, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009224735470287005}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a49e9c018a658f8a7dde81733e8f459e71aab46f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2908249158249158, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009318815921176653}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.27441077441077444, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009156177122244528}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8bb754018ab9424e3640c15366935ce12005091f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2824074074074074, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009237303403479332}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.2756734006734007, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009169229476542563}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..7e855d73db30b6d526151935f6be6ea6b502af51 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2781986531986532, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0091950596015839}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.2727272727272727, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00913863072636423}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..5fa97a8aabc2c0d483d6e787e588702504d83311 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_arc_easy_qa_options_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "arc_easy", "prompt_name": "qa_options", "acc": 0.2824074074074074, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009237303403479334}, {"task_name": "arc_easy", "prompt_name": "qa_options", "acc_norm": 0.27146464646464646, "fixed_answer_choice_list": null, "dataset_path": "ai2_arc", "dataset_name": "ARC-Easy", "subset": null, "prompt_id": "252aa566-9482-4e81-aad9-664a9bebd8e8", "prompt_jinja": "{{question}}\n\nOptions:\n- {{answer_choices | join(\"\\n- \")}}|||\n{{answer_choices[choices[\"label\"].index(answerKey)]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009125362970360623}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..0804443f3b9a02175b5b91e196afa6ec0cdcd97d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc": 0.48933333333333334, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009128153252511649}, {"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc_norm": 0.6233333333333333, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00884811049411477}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..85177da69af2c1a03be69abec1dd468243cb637b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc": 0.5403333333333333, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009100476927108948}, {"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc_norm": 0.5463333333333333, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00909094544975723}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..7c082a9df2ff912c1ef6fe329812d0cb60d62721 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc": 0.5376666666666666, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00910428672401049}, {"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc_norm": 0.5733333333333334, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009031496556538196}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9dae2a54f3f27701151d87ece227f11a48ac0d99 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc": 0.561, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009062029213030572}, {"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc_norm": 0.5776666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009019409415904176}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..a32a7e17e96f46ce25a0c30d718b78ab7f3b3906 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc": 0.5606666666666666, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009062775319073724}, {"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc_norm": 0.575, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009026931658379627}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..32b7e0541dc20777b0c6a3c134d10b6b634da2a1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_GPT-3-Style_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc": 0.564, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009055127374988182}, {"task_name": "boolq", "prompt_name": "GPT-3 Style", "acc_norm": 0.581, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "492f0f88-4370-46cd-839b-1de37a55aeda", "prompt_jinja": "{{ passage }} \nQuestion: {{ question }}\nAnswer: ||| \n{% if label != -1 %}\n{{ answer_choices[label] }}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009009627690997004}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e3d9ebae76803e6f2aaeed065942461268cba168 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "after_reading", "acc": 0.6196666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008864883436857793}, {"task_name": "boolq", "prompt_name": "after_reading", "acc_norm": 0.485, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009126121594912155}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b9c1a5a6f07a3be4641cba2fbd1874a7a026735c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "after_reading", "acc": 0.5406666666666666, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009099982269204863}, {"task_name": "boolq", "prompt_name": "after_reading", "acc_norm": 0.5403333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009100476927108948}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_2.json new file mode 100644 index 0000000000000000000000000000000000000000..77961c2d6e8e75fdf5c46a66846599e87be9c4fd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "after_reading", "acc": 0.5213333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009121916798841863}, {"task_name": "boolq", "prompt_name": "after_reading", "acc_norm": 0.5053333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009129711700290994}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3abf69791f8892d11806dcc06b1a221af8976fa4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "after_reading", "acc": 0.55, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009084465266030921}, {"task_name": "boolq", "prompt_name": "after_reading", "acc_norm": 0.545, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009093178503605498}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_4.json new file mode 100644 index 0000000000000000000000000000000000000000..7a5ecf1a3c3899fae0b8247af2fc8d63be2d46f0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "after_reading", "acc": 0.5443333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00909427038138736}, {"task_name": "boolq", "prompt_name": "after_reading", "acc_norm": 0.536, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009106534814375938}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_5.json new file mode 100644 index 0000000000000000000000000000000000000000..3158b64f8908831acd54ae0385b9e925ef280485 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_after_reading_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "after_reading", "acc": 0.5556666666666666, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00907346956924853}, {"task_name": "boolq", "prompt_name": "after_reading", "acc_norm": 0.5493333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "3e386463-1715-4578-9cba-07d11a0d3b61", "prompt_jinja": "Passage: {{passage}}\n\nAfter reading this passage, I have a question: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009085680525105019}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c54c95de5335b679f7e482a03d134817e3984734 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "exercise", "acc": 0.6203333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008861873799148993}, {"task_name": "boolq", "prompt_name": "exercise", "acc_norm": 0.38166666666666665, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008870849530787627}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_1.json new file mode 100644 index 0000000000000000000000000000000000000000..edfbfacad9443c3d41ad7b0c4a57437acf9ff1ac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "exercise", "acc": 0.5406666666666666, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009099982269204863}, {"task_name": "boolq", "prompt_name": "exercise", "acc_norm": 0.541, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009099483512819305}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_2.json new file mode 100644 index 0000000000000000000000000000000000000000..652979ef45507c0695c94f3f52e2f4929faaa084 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "exercise", "acc": 0.56, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009064255084676055}, {"task_name": "boolq", "prompt_name": "exercise", "acc_norm": 0.5536666666666666, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00907748661345029}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_3.json new file mode 100644 index 0000000000000000000000000000000000000000..16ff14f4002f5ce032c775e77cdc5d1e0b250057 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "exercise", "acc": 0.5726666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009033293159951222}, {"task_name": "boolq", "prompt_name": "exercise", "acc_norm": 0.564, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009055127374988184}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_4.json new file mode 100644 index 0000000000000000000000000000000000000000..1ea32e2288ae45381ae9de631078c78a0689867b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "exercise", "acc": 0.581, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009009627690997004}, {"task_name": "boolq", "prompt_name": "exercise", "acc_norm": 0.5686666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00904372116961954}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_5.json new file mode 100644 index 0000000000000000000000000000000000000000..699bf606d9a0edf3193b293c387134bebc02192c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_exercise_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "exercise", "acc": 0.5846666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008998379972670818}, {"task_name": "boolq", "prompt_name": "exercise", "acc_norm": 0.579, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "9f4c6b0a-437b-40c0-b467-db4b7218d38d", "prompt_jinja": "Exercise: read the text and answer the question by True or False.\n\nText: {{passage}}\nQuestion: {{question}}? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009015547313638383}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d7acc20945a43dd0237d739674a09e121c5f0e3e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "valid_binary", "acc": 0.5126666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00912730086383017}, {"task_name": "boolq", "prompt_name": "valid_binary", "acc_norm": 0.3893333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00890378508047089}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..bc478258dab0b9e2356a7536479cf7512b7023e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "valid_binary", "acc": 0.5403333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009100476927108948}, {"task_name": "boolq", "prompt_name": "valid_binary", "acc_norm": 0.5403333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009100476927108948}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..7fcbb231514880d602e29350d63f5f227c9d3d28 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "valid_binary", "acc": 0.556, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009072785596468857}, {"task_name": "boolq", "prompt_name": "valid_binary", "acc_norm": 0.542, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009097962646004978}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..dab3fbf1db813406c1d14020c6e1385408db3979 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "valid_binary", "acc": 0.5573333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009070008341418438}, {"task_name": "boolq", "prompt_name": "valid_binary", "acc_norm": 0.5473333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.009089227499483243}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..1dc24a7d8ef693608e4fa95ba8174466ce961384 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "valid_binary", "acc": 0.5676666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.009046234144187919}, {"task_name": "boolq", "prompt_name": "valid_binary", "acc_norm": 0.5533333333333333, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00907814166393873}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..187308100088f5a50ff581b888ebbf874c725cfb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_valid_binary_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "valid_binary", "acc": 0.5763333333333334, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0090232041691723}, {"task_name": "boolq", "prompt_name": "valid_binary", "acc_norm": 0.5696666666666667, "fixed_answer_choice_list": ["False", "True"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "eb78772c-e81e-4b8a-a77b-b75efd1c212a", "prompt_jinja": "{{passage}}\n\nQ: {{question}}? True or False? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00904117061597785}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_0.json new file mode 100644 index 0000000000000000000000000000000000000000..911060f30ff8db8a850e604e8f6f774855f0ac5c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "yes_no_question", "acc": 0.6236666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008846558976258922}, {"task_name": "boolq", "prompt_name": "yes_no_question", "acc_norm": 0.6236666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008846558976258922}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c71b737ceb334caf3aa9d89d49271f46a1d14a72 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "yes_no_question", "acc": 0.6153333333333333, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00888401463187693}, {"task_name": "boolq", "prompt_name": "yes_no_question", "acc_norm": 0.624, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008845002997512754}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_2.json new file mode 100644 index 0000000000000000000000000000000000000000..83a208544dd1568112505eaf7e46d1587350a801 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "yes_no_question", "acc": 0.6126666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008895417372116209}, {"task_name": "boolq", "prompt_name": "yes_no_question", "acc_norm": 0.622, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00885427200344005}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_3.json new file mode 100644 index 0000000000000000000000000000000000000000..cffb9c0ab81de7dbfeefad2e95c6f8ba96761210 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "yes_no_question", "acc": 0.613, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008894007408882734}, {"task_name": "boolq", "prompt_name": "yes_no_question", "acc_norm": 0.6156666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008882569490543052}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_4.json new file mode 100644 index 0000000000000000000000000000000000000000..312e969a3d7ae265943725a73f62425306cf3384 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "yes_no_question", "acc": 0.6226666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.00885120015653439}, {"task_name": "boolq", "prompt_name": "yes_no_question", "acc_norm": 0.624, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.00884500299751275}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d0809ce843041c8901db5783bd6a8e63925b1b61 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_boolq_yes_no_question_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "boolq", "prompt_name": "yes_no_question", "acc": 0.6216666666666667, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.008855801251873017}, {"task_name": "boolq", "prompt_name": "yes_no_question", "acc_norm": 0.624, "fixed_answer_choice_list": ["No", "Yes"], "dataset_path": "super_glue", "dataset_name": "boolq", "subset": null, "prompt_id": "7cf7acdf-e3a2-459f-a3e8-2e2d27dd6aa5", "prompt_jinja": "Text: {{passage}}\n\nAnswer the following yes/no question: {{question}}? Yes or no? |||\n{% if label != -1 %}\n{{answer_choices[label]}}\n{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.008845002997512754}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a6513a783cf09d54f6735a8d283ed473583c0484 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "GPT-3 style", "acc": 0.32142857142857145, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06297362289056341}, {"task_name": "cb", "prompt_name": "GPT-3 style", "f1": 0.16666666666666666, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..ccd13f7822c5d6033079cfd435fc5472e1405a2e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "GPT-3 style", "acc": 0.35714285714285715, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06460957383809221}, {"task_name": "cb", "prompt_name": "GPT-3 style", "f1": 0.2247097844112769, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..08d1742dc227d216091e8622c8cf63289a3a2896 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "GPT-3 style", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0663363415035954}, {"task_name": "cb", "prompt_name": "GPT-3 style", "f1": 0.24232804232804236, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7ddccad5b91feac7a135e41c8423a994d2a3b27e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "GPT-3 style", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0658538889806635}, {"task_name": "cb", "prompt_name": "GPT-3 style", "f1": 0.2075, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bc0d43eabe804d46fb6ff66dca7f023cfa1f0366 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "GPT-3 style", "acc": 0.375, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06527912098338669}, {"task_name": "cb", "prompt_name": "GPT-3 style", "f1": 0.18421052631578946, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..5888fdfc62dc1050f4aa8293efb1050c5d8f4dbe --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_GPT-3-style_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "GPT-3 style", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0658538889806635}, {"task_name": "cb", "prompt_name": "GPT-3 style", "f1": 0.19047619047619047, "fixed_answer_choice_list": ["True", "False", "Neither"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "75db2bc2-3caa-4956-9653-13c7dd6255df", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..21f7c2210a31c2e92f95ad77a9abda9ca60692ac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "MNLI crowdsource", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06633634150359538}, {"task_name": "cb", "prompt_name": "MNLI crowdsource", "f1": 0.1940928270042194, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f2306038cba6e310ee0fb6804ba7c40033045671 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "MNLI crowdsource", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0658538889806635}, {"task_name": "cb", "prompt_name": "MNLI crowdsource", "f1": 0.2842025699168556, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..301b622559c61118e5dd0fe2d2a0be46bfc9f371 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "MNLI crowdsource", "acc": 0.42857142857142855, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06672848092813058}, {"task_name": "cb", "prompt_name": "MNLI crowdsource", "f1": 0.29715109989181393, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9723bf5abf591ddc9af0af9a33d9045fbcaca26e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "MNLI crowdsource", "acc": 0.44642857142857145, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.067031892279424}, {"task_name": "cb", "prompt_name": "MNLI crowdsource", "f1": 0.31340255400405775, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..a77d29b38565515fba0d116e3ca939aab383e585 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "MNLI crowdsource", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06585388898066351}, {"task_name": "cb", "prompt_name": "MNLI crowdsource", "f1": 0.2647907647907648, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4394367cb9390b7ec8ad02ba03a65d592dde083d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_MNLI-crowdsource_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "MNLI crowdsource", "acc": 0.35714285714285715, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0646095738380922}, {"task_name": "cb", "prompt_name": "MNLI crowdsource", "f1": 0.24618343550907562, "fixed_answer_choice_list": ["Correct", "Incorrect", "Inconclusive"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "bee62bfa-5307-4e1c-97b2-2ad2f7bcb179", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, \"{{hypothesis}}\" is definitely correct, incorrect, or inconclusive? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..1468544ce6b62fdda67574e58c27e4ec67cdb0e2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "can we infer", "acc": 0.42857142857142855, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06672848092813058}, {"task_name": "cb", "prompt_name": "can we infer", "f1": 0.2791044776119403, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..44e0d1a646de57636c1725dc282b8de4113f4066 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "can we infer", "acc": 0.4642857142857143, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0672477765493766}, {"task_name": "cb", "prompt_name": "can we infer", "f1": 0.3227969348659004, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..fed113f9d966df0802d86caf28fba22bf9046c45 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "can we infer", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06633634150359541}, {"task_name": "cb", "prompt_name": "can we infer", "f1": 0.27519379844961245, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8f48de23ca5890132e55500a52af7d1c0088d488 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "can we infer", "acc": 0.4642857142857143, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0672477765493766}, {"task_name": "cb", "prompt_name": "can we infer", "f1": 0.311531007751938, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..4821e5ef45924fac96977fae70c5cd59b34ec8df --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "can we infer", "acc": 0.42857142857142855, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06672848092813058}, {"task_name": "cb", "prompt_name": "can we infer", "f1": 0.2905242905242906, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..062f984302fd4ac14f96bcbbebd0501e7b6bef83 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_can-we-infer_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "can we infer", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0663363415035954}, {"task_name": "cb", "prompt_name": "can we infer", "f1": 0.2798088410991637, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "2e76cd0f-68ca-4f03-83ed-11cf15b25a84", "prompt_jinja": "Suppose {{premise}} Can we infer that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %} ", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..68f24c556ed1d218e9f27e481c63e331c9fe406f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0658538889806635}, {"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "f1": 0.3166447079490558, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..97f1d5468d13446a50b513c516e13a35d3d567c3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0658538889806635}, {"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "f1": 0.2842025699168556, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e22eef54a711f44daa33df529b58a7739549ffbd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "acc": 0.44642857142857145, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06703189227942398}, {"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "f1": 0.29843652282676675, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..94c0e37a01ac383890077be572ec2a6bb1eecd19 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06633634150359541}, {"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "f1": 0.23085585585585586, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b2f46dade1f4fc5a6e1cb7292d7e6bf18ec03dfc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "acc": 0.5178571428571429, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06737697508644647}, {"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "f1": 0.2908378541289934, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..95305e8ee8aa75746d2caf1830cb38cacc6f0f53 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "acc": 0.5, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06741998624632421}, {"task_name": "cb", "prompt_name": "guaranteed/possible/impossible", "f1": 0.2660493827160494, "fixed_answer_choice_list": ["Guaranteed", "Impossible", "Possible"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "90ab1002-093c-4e54-b48f-626655e36b65", "prompt_jinja": "Assume it is true that {{premise}} \n\nTherefore, \"{{hypothesis}}\" is {{\"guaranteed\"}}, {{\"possible\"}}, or {{\"impossible\"}}? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..cc456e991437b0148a53516ffa70e9147077578c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "justified in saying", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06633634150359538}, {"task_name": "cb", "prompt_name": "justified in saying", "f1": 0.2144878324844369, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cf8361e07554080a5fdf739359e10cfc112ea467 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "justified in saying", "acc": 0.4642857142857143, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0672477765493766}, {"task_name": "cb", "prompt_name": "justified in saying", "f1": 0.3227969348659004, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..3d9a95caceeee3e641b7115aa2390106ea1fb907 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "justified in saying", "acc": 0.4107142857142857, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06633634150359541}, {"task_name": "cb", "prompt_name": "justified in saying", "f1": 0.27519379844961245, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..bae53a80b5f8bfe462c67449c30f01b6c020881d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "justified in saying", "acc": 0.44642857142857145, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.067031892279424}, {"task_name": "cb", "prompt_name": "justified in saying", "f1": 0.29572649572649573, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..025206d6cc723f0c7bda6325ae04031658619cfe --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "justified in saying", "acc": 0.42857142857142855, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.06672848092813058}, {"task_name": "cb", "prompt_name": "justified in saying", "f1": 0.2854700854700854, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d447760a5a0142555f44fd7b6c1a2922156a1a68 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_cb_justified-in-saying_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "cb", "prompt_name": "justified in saying", "acc": 0.39285714285714285, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0658538889806635}, {"task_name": "cb", "prompt_name": "justified in saying", "f1": 0.2524875621890547, "fixed_answer_choice_list": ["Yes", "No", "Maybe"], "dataset_path": "super_glue", "dataset_name": "cb", "subset": null, "prompt_id": "5c9b1fa9-93f0-4f82-b9e3-e0967e4d7260", "prompt_jinja": "{{premise}} Are we justified in saying that \"{{hypothesis}}\"? Yes, no, or maybe? ||| {% if label !=-1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": ""}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a95dc325a7b39b69d6de68ce788a234cebbaebd3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "best_option", "acc": 0.58, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.049604496374885836}, {"task_name": "copa", "prompt_name": "best_option", "acc_norm": 0.5, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050251890762960605}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_1.json new file mode 100644 index 0000000000000000000000000000000000000000..94791759f7c093d5732d49e5cc404e454a1b38fd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "best_option", "acc": 0.53, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05016135580465919}, {"task_name": "copa", "prompt_name": "best_option", "acc_norm": 0.47, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05016135580465919}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_2.json new file mode 100644 index 0000000000000000000000000000000000000000..81b3bff0cef2d6f8c3bdfd1844f318361b07da70 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "best_option", "acc": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05}, {"task_name": "copa", "prompt_name": "best_option", "acc_norm": 0.49, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956912}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_3.json new file mode 100644 index 0000000000000000000000000000000000000000..62241e39d8ecf390bbd8486a43ebb135ec93d3e1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "best_option", "acc": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05}, {"task_name": "copa", "prompt_name": "best_option", "acc_norm": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c52f775ec3e0cb43c2736f0607399186b2d471c5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "best_option", "acc": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05024183937956911}, {"task_name": "copa", "prompt_name": "best_option", "acc_norm": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956911}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_5.json new file mode 100644 index 0000000000000000000000000000000000000000..42434c9aef5f1fe06c7ebd2dcb9ec813f3dc536d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_best_option_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "best_option", "acc": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05}, {"task_name": "copa", "prompt_name": "best_option", "acc_norm": 0.59, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "8ce80f8a-239e-4393-892c-f63dbb0d9929", "prompt_jinja": "{{ premise }} \n\nWhat's the best option?\n- {{choice1}}\n- {{choice2}}\n\nWe are looking for {% if question == \"cause\" %} a cause {% else %} an effect {% endif %}\n||| {% if label != -1 %}{{answer_choices[label]}}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.04943110704237101}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_0.json new file mode 100644 index 0000000000000000000000000000000000000000..8442f5d5e2fef6b8e434d1e6039255026b2510c1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "cause_effect", "acc": 0.59, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.049431107042371025}, {"task_name": "copa", "prompt_name": "cause_effect", "acc_norm": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956912}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c9a98a9c1605658c3425e26526ab8e0f5f3afc50 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "cause_effect", "acc": 0.54, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05009082659620332}, {"task_name": "copa", "prompt_name": "cause_effect", "acc_norm": 0.46, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05009082659620332}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_2.json new file mode 100644 index 0000000000000000000000000000000000000000..9ddc38986686a0c8dad7d3a711d79167755c4203 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "cause_effect", "acc": 0.56, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.04988876515698589}, {"task_name": "copa", "prompt_name": "cause_effect", "acc_norm": 0.48, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_3.json new file mode 100644 index 0000000000000000000000000000000000000000..2ce48f09149f45e499c6433d07cd9a1438fcd445 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "cause_effect", "acc": 0.54, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05009082659620333}, {"task_name": "copa", "prompt_name": "cause_effect", "acc_norm": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_4.json new file mode 100644 index 0000000000000000000000000000000000000000..f464640495ad0208379128731babfef86e31bda4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "cause_effect", "acc": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05}, {"task_name": "copa", "prompt_name": "cause_effect", "acc_norm": 0.54, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05009082659620333}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d3ad0311aa7b0f79b5adb24e51b979cf57d43843 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_cause_effect_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "cause_effect", "acc": 0.54, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05009082659620333}, {"task_name": "copa", "prompt_name": "cause_effect", "acc_norm": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "a61d8c21-da25-47bf-b5fe-14a8edd650af", "prompt_jinja": "{{ premise }}\n\nSelect the most plausible {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_0.json new file mode 100644 index 0000000000000000000000000000000000000000..061d4d44209d23b174515fc976739f414fe52a3b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "choose", "acc": 0.58, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.049604496374885836}, {"task_name": "copa", "prompt_name": "choose", "acc_norm": 0.54, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05009082659620332}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_1.json new file mode 100644 index 0000000000000000000000000000000000000000..ee5aef2b156f633e887a508a55d67cffc4718286 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "choose", "acc": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05}, {"task_name": "copa", "prompt_name": "choose", "acc_norm": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2303ef6752d9752135038acd8059de49750c76ac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "choose", "acc": 0.55, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05}, {"task_name": "copa", "prompt_name": "choose", "acc_norm": 0.49, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956912}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ee721225579ee601bb3d9e3ec16b0709205c71e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "choose", "acc": 0.53, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05016135580465919}, {"task_name": "copa", "prompt_name": "choose", "acc_norm": 0.5, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050251890762960605}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_4.json new file mode 100644 index 0000000000000000000000000000000000000000..9d443ef4d6e8ce8c3521bd97b002e0c34824c64c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "choose", "acc": 0.54, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05009082659620333}, {"task_name": "copa", "prompt_name": "choose", "acc_norm": 0.49, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956912}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_5.json new file mode 100644 index 0000000000000000000000000000000000000000..cf2b2b895298df6f14b5fdef426eedddebf198f7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_choose_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "choose", "acc": 0.53, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050161355804659205}, {"task_name": "copa", "prompt_name": "choose", "acc_norm": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "f32348cd-d3cb-4619-87b9-e24f99c78567", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} because... {% else %} so... {% endif %}\nChoose between:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_0.json new file mode 100644 index 0000000000000000000000000000000000000000..91dda2b90f1579fee135c1e1218d2453a7c62538 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "i_am_hesitating", "acc": 0.56, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.049888765156985884}, {"task_name": "copa", "prompt_name": "i_am_hesitating", "acc_norm": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956912}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_1.json new file mode 100644 index 0000000000000000000000000000000000000000..1d0a67cbe3d66d11af56eee6b72f6dccccd81ffc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "i_am_hesitating", "acc": 0.48, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050211673156867795}, {"task_name": "copa", "prompt_name": "i_am_hesitating", "acc_norm": 0.45, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.049999999999999996}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_2.json new file mode 100644 index 0000000000000000000000000000000000000000..c19d092f0b52c32f1e01e0ba64e06f53f96687e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "i_am_hesitating", "acc": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050211673156867795}, {"task_name": "copa", "prompt_name": "i_am_hesitating", "acc_norm": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_3.json new file mode 100644 index 0000000000000000000000000000000000000000..035fd5532f44e75250dd43ead5c13a4c1a3be776 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "i_am_hesitating", "acc": 0.49, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05024183937956912}, {"task_name": "copa", "prompt_name": "i_am_hesitating", "acc_norm": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956911}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8d4ba770fe51af04c5e9d790df1cc99783c5b073 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "i_am_hesitating", "acc": 0.47, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05016135580465919}, {"task_name": "copa", "prompt_name": "i_am_hesitating", "acc_norm": 0.5, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050251890762960605}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d606ab92bb825976c43f68b8ff1dbaec2436c803 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_i_am_hesitating_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "i_am_hesitating", "acc": 0.5, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050251890762960605}, {"task_name": "copa", "prompt_name": "i_am_hesitating", "acc_norm": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "4d879cbe-2fd7-424a-9d78-3f5200313fba", "prompt_jinja": "{{ premise }} \n\nI am hesitating between two options. Help me choose the more likely {% if question == \"cause\" %} cause: {% else %} effect: {% endif %}\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956911}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_0.json new file mode 100644 index 0000000000000000000000000000000000000000..107cc5f71c513fc391674eacbfdf6b35e2292606 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "plausible_alternatives", "acc": 0.56, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.049888765156985884}, {"task_name": "copa", "prompt_name": "plausible_alternatives", "acc_norm": 0.5, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050251890762960605}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_1.json new file mode 100644 index 0000000000000000000000000000000000000000..6a302a1166f918fa47d2e90600ffee5146396704 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "plausible_alternatives", "acc": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050211673156867795}, {"task_name": "copa", "prompt_name": "plausible_alternatives", "acc_norm": 0.46, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05009082659620332}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d8e557c583d3760f95879fdf2bc8eb0878781098 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "plausible_alternatives", "acc": 0.53, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050161355804659205}, {"task_name": "copa", "prompt_name": "plausible_alternatives", "acc_norm": 0.48, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_3.json new file mode 100644 index 0000000000000000000000000000000000000000..74aaaaf062a5770b317af09aae27a873a85c986d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "plausible_alternatives", "acc": 0.52, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.050211673156867795}, {"task_name": "copa", "prompt_name": "plausible_alternatives", "acc_norm": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.05024183937956911}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bb4fea6a08e8ae45cdf54ec21e326b9a9accd0c5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "plausible_alternatives", "acc": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05024183937956911}, {"task_name": "copa", "prompt_name": "plausible_alternatives", "acc_norm": 0.48, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_5.json new file mode 100644 index 0000000000000000000000000000000000000000..cfc28119ab9dbcb0e3a8dc67d26b73061f3a6a93 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_copa_plausible_alternatives_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "copa", "prompt_name": "plausible_alternatives", "acc": 0.51, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.05024183937956911}, {"task_name": "copa", "prompt_name": "plausible_alternatives", "acc_norm": 0.48, "fixed_answer_choice_list": null, "dataset_path": "super_glue", "dataset_name": "copa", "subset": null, "prompt_id": "66ea075e-4d03-4a78-b1fa-9a5228cf0c9d", "prompt_jinja": "{{ premise }} {% if question == \"cause\" %} This happened because... {% else %} As a consequence... {% endif %}\nHelp me pick the more plausible option:\n- {{choice1}}\n- {{choice2}} ||| {% if label != -1 %}{{ answer_choices[label] }}{%endif%}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.050211673156867795}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.json new file mode 100644 index 0000000000000000000000000000000000000000..03bdd2a94e4a265d57b18e66bc9909eb94a65fac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "bleu": 1.4085336184354111, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05741951405804131}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_precision": 0.13228526132614984, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0020013074393031836}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_recall": 0.2369325887389989, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0027790980608073646}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_fmeasure": 0.16506378620343637, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022294407692459474}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_precision": 0.034003030527238576, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010025662026581091}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_recall": 0.056957962707056595, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016005937753295783}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_fmeasure": 0.0413168613300981, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011779113504419888}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_precision": 0.11307449761220935, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012999325612706172}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_recall": 0.208842612528325, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0020062255755377858}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_fmeasure": 0.14268631130584333, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014826828522232203}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_precision": 0.10960115777847065, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001579915881101131}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_recall": 0.19748155077377938, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022590044053826777}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_fmeasure": 0.13688623513784934, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017661120751764666}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.json new file mode 100644 index 0000000000000000000000000000000000000000..aa62c580241d548f4b3de56a63a3178f53b3ea57 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "bleu": 4.729286166275417, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09128304389641625}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_precision": 0.3408358446419251, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0034116541291492057}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_recall": 0.2783365471883401, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002737152709268981}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_fmeasure": 0.2892038317215652, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0025869454710142777}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_precision": 0.11786217798858512, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0020524631363241412}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_recall": 0.09241456760956686, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015313690129086298}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_fmeasure": 0.09705173957954942, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015453194099685405}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_precision": 0.25216134633862136, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027436356295732754}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_recall": 0.20399063384073168, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002098237813401181}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_fmeasure": 0.21222627239556746, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0019998631000071967}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_precision": 0.28273246045224193, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0030427081908894252}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_recall": 0.22924073727175148, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0023626083063246254}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_fmeasure": 0.23867678360949154, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0022704869608702}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2b171c501e32c0182b543e589d559dc1cec43c21 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "bleu": 6.325316845200212, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09823383956529014}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_precision": 0.3908301753738232, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031422044941371253}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_recall": 0.32494169596300476, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024924666531749825}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_fmeasure": 0.33385083240638835, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022057300734858753}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_precision": 0.1514609363136513, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022477501689905873}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_recall": 0.12052118677866239, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016199084429215386}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_fmeasure": 0.12480576931000954, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001582754162108835}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_precision": 0.293562283125087, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002707140102409516}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_recall": 0.24127140452116988, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019870656915090814}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_fmeasure": 0.2482760515483937, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017935997104643916}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_precision": 0.32736403463849806, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002914041154580964}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_recall": 0.2701473844458722, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022228285101149096}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_fmeasure": 0.27814692011572395, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00202476127925843}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.json new file mode 100644 index 0000000000000000000000000000000000000000..19e7a410e83add3edb649e8df229530b5e707622 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "bleu": 7.093242387648388, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1779108642695036}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_precision": 0.4033568597868611, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0030439856617461825}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_recall": 0.3393497221509125, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024495138617378286}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_fmeasure": 0.3468468278255215, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002126607440022899}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_precision": 0.1603885963824591, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002211321437110491}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_recall": 0.1297128662599877, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016715601470477192}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_fmeasure": 0.13345925813528606, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016050391064121614}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_precision": 0.30327882804864414, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0026682405889953253}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_recall": 0.2518780545862424, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019409034909989161}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_fmeasure": 0.25781869559651055, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017250105332014863}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_precision": 0.33832600518727873, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002866030451437672}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_recall": 0.2824307369414572, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021987427091062425}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_fmeasure": 0.28922616836791826, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019740744474346238}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.json new file mode 100644 index 0000000000000000000000000000000000000000..04720805eab63e6c55aa1b64ab1fe2fc2e4a8e99 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "bleu": 7.441380932329685, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.13415864466690663}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_precision": 0.40930270509361055, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003082794337886431}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_recall": 0.34406073111724306, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024467984658659457}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_fmeasure": 0.3513421927671594, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021279258327609294}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_precision": 0.16770678005567702, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022910300764590334}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_recall": 0.1356936401482478, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017118286189666942}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_fmeasure": 0.139368667490815, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016374065418968793}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_precision": 0.30955103142076024, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0026954850190455738}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_recall": 0.25780563970283943, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019854199620409053}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_fmeasure": 0.2632971395760134, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001761093443585716}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_precision": 0.34462560843141665, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0028969602572112584}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_recall": 0.2875465717034684, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002202341197956502}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_fmeasure": 0.294208873461138, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001978637458277599}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.json new file mode 100644 index 0000000000000000000000000000000000000000..3be52679238de6b158fa32e5c74bd6e837b711e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "bleu": 7.5737114766827744, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.16631977129206255}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_precision": 0.41687585365688856, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031195723945421903}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_recall": 0.3459752611920822, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002424143041978818}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge1_fmeasure": 0.3550742864577696, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021015187822019713}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_precision": 0.1733553595449332, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0023061322348589372}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_recall": 0.13907964535601638, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001719596537412042}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rouge2_fmeasure": 0.1433273164318412, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016448122877788167}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_precision": 0.3185451706746064, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002764987760129163}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_recall": 0.2618919651726129, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001983008971819947}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeL_fmeasure": 0.2689262922478298, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017684452634382998}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_precision": 0.353237732771995, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029473597771023205}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_recall": 0.2916978400324908, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022123740894828313}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "coherent_text", "rougeLsum_fmeasure": 0.29967975079613524, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "bdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Please generate a restaurant description from the information given below:\n\n{{meaning_representation}} ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001985017926935537}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.json new file mode 100644 index 0000000000000000000000000000000000000000..abc6151ea3cdce3b01c858380f5dca2da158d8f0 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "bleu": 2.703242330052237, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.053740475370982206}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_precision": 0.2661363538943579, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002367715966031621}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_recall": 0.43300283554036917, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004390407342450644}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_fmeasure": 0.3195200501284644, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0029128906590861338}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_precision": 0.11474242753676482, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010312600650423582}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_recall": 0.1866895759452563, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002052535203353899}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_fmeasure": 0.13691922129643072, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0012702596895246712}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_precision": 0.17937558305738294, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013720245995724903}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_recall": 0.28616889513557914, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0026317983935095325}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_fmeasure": 0.21271540347370638, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016500637313875428}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_precision": 0.21948638044662674, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018609668228193143}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_recall": 0.3521509345321294, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00340514324563439}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_fmeasure": 0.26161394912968283, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0022526565471884855}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.json new file mode 100644 index 0000000000000000000000000000000000000000..af3c5f6ea8dcefb832fe36b0249a453db4870ddb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "bleu": 4.577776049140263, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09034061701953547}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_precision": 0.34100807827295837, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003184063014013613}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_recall": 0.27941656720882674, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0026026095744065953}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_fmeasure": 0.29090627143470194, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0024330971957175203}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_precision": 0.11175648476464418, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0019681372052978165}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_recall": 0.08832198666750592, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0014790311360637835}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_fmeasure": 0.09291021571347792, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015027135995425269}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_precision": 0.25053169214166077, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0025671894408817466}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_recall": 0.20342961186323133, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001994180509072628}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_fmeasure": 0.21213952158968352, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018872143094313097}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_precision": 0.28172377076654426, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002852857226376121}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_recall": 0.22946240670401793, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002255076858855054}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_fmeasure": 0.2393285330033846, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00214964727816577}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.json new file mode 100644 index 0000000000000000000000000000000000000000..898a4e6dd0402e01549f907cd314c400b2b0a740 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "bleu": 5.98205212345435, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1280571718069931}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_precision": 0.3823214924637971, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003024709228079845}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_recall": 0.3204650885914036, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002430593485338909}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_fmeasure": 0.32884340089308617, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002135142045723192}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_precision": 0.14073383940982426, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002136791451462909}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_recall": 0.11362566019027333, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001592486151354374}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_fmeasure": 0.11731827518171299, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015444189662990626}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_precision": 0.2851163980403521, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002571830567593308}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_recall": 0.2366396569421376, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019279427376296453}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_fmeasure": 0.24308318109830301, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001718910616546924}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_precision": 0.31962238317070146, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002803107271378859}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_recall": 0.26621396952055804, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002177094542934803}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_fmeasure": 0.2736078163019124, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001965703958545944}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.json new file mode 100644 index 0000000000000000000000000000000000000000..b54535a5ebeef4fda1d33787fdd5738114da2f7c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "bleu": 6.863369305798137, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.15945748355314382}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_precision": 0.39244673058197366, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.00291042027182271}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_recall": 0.3356108550535503, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002419884948866489}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_fmeasure": 0.342206180898298, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021010446350658595}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_precision": 0.149747180591347, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002068565282156403}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_recall": 0.12431399945617358, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016576108529010333}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_fmeasure": 0.12734114879849334, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001589185479506862}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_precision": 0.2929476916339765, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00249955074163189}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_recall": 0.24778818042905212, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019126314450433883}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_fmeasure": 0.25304733592238204, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017029355919681117}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_precision": 0.32865423091372126, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0027286585155264402}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_recall": 0.2790170412547052, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021770844165001626}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_fmeasure": 0.2851145615546105, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019583190063539803}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.json new file mode 100644 index 0000000000000000000000000000000000000000..55d8b336ec6ea1d9fef25bf989e4c3d0a1fe522e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "bleu": 7.213329948258112, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1504445078411636}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_precision": 0.39870625613730687, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0030059139760784137}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_recall": 0.3401793704440513, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00244816453017379}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_fmeasure": 0.34597281761424564, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021117138542066263}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_precision": 0.15639401362724684, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002182860663855212}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_recall": 0.12970046691236706, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001719867215235167}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_fmeasure": 0.1322742849122928, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016280655196310467}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_precision": 0.30042871354521805, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002604676027141301}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_recall": 0.2538632272987309, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019749848838672476}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_fmeasure": 0.25839347897511217, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001739652960879094}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_precision": 0.33569946464927397, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002827255616797676}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_recall": 0.2846056877350737, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002227786950064511}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_fmeasure": 0.2899260055449036, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019853018337260124}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.json new file mode 100644 index 0000000000000000000000000000000000000000..6a24aa58a209d29635d384784d09279049566131 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "bleu": 7.496072350547459, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.13118615529748254}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_precision": 0.4079186719686208, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0030636128374210455}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_recall": 0.34551384483174236, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024411037115400777}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge1_fmeasure": 0.3526218995116698, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021169320380915397}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_precision": 0.1651169143111655, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022498261971629634}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_recall": 0.13570208053691146, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017306096236515535}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rouge2_fmeasure": 0.13899954079181534, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016519779895088726}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_precision": 0.3103180907026251, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0026794184035727514}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_recall": 0.260674271635608, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019926530246205786}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeL_fmeasure": 0.26611116257409023, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017655608447914495}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_precision": 0.34494793963685744, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002867601551740783}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_recall": 0.290738713102737, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022139980383301975}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "create_text_for_me", "rougeLsum_fmeasure": 0.29700738879576205, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "711bcf63-be82-4937-bdef-0c379d20bb74", "prompt_jinja": "How would we create an appropriate text out of the following data?\n{{meaning_representation}}\n\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019763199856062843}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.json new file mode 100644 index 0000000000000000000000000000000000000000..259e3949e5a63721096ba66a9db1cdef78a11288 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "bleu": 3.33689116446375, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.061087011177673324}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_precision": 0.16350018472386488, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0009748274524219786}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_recall": 0.15345481937904124, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0013096963261815264}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_fmeasure": 0.1544874561171709, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0010331568296333966}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_precision": 0.10930581072628082, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009544493807060682}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_recall": 0.10394007426189322, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0011356818972608751}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_fmeasure": 0.10374767270154109, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009552767021848785}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_precision": 0.16350018472386488, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0009748274524219786}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_recall": 0.15345481937904124, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0013096963261815264}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_fmeasure": 0.1544874561171709, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0010331568296333966}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_precision": 0.16126223153775923, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0009358067078434506}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_recall": 0.15130017670533033, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0012746322385110529}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_fmeasure": 0.15232644862442798, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.000994235301055403}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.json new file mode 100644 index 0000000000000000000000000000000000000000..767a7a3949249ab76ec6f8b47b6c5cb88f7e2bc2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "bleu": 4.231103023669522, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06401228873780763}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_precision": 0.22876696491722354, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002309289082178887}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_recall": 0.22418518523376774, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024608018120844447}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_fmeasure": 0.21822213931750256, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002101989165296421}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_precision": 0.11900463798533546, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0013220328662893331}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_recall": 0.11426547711399747, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0013755970980597794}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_fmeasure": 0.11246784846792322, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011969645761367486}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_precision": 0.19721866991989792, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001448486033755209}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_recall": 0.19219429418598927, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001702222043237259}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_fmeasure": 0.18786846421672448, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001330092385386827}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_precision": 0.2036594715170169, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017870596309090383}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_recall": 0.19919852385897865, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002011582797896158}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_fmeasure": 0.19423470819963112, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001652146284622351}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.json new file mode 100644 index 0000000000000000000000000000000000000000..452ade9e88a88979bfe44fba10b4eb8ea993f47a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "bleu": 5.525451650396909, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1444467494539742}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_precision": 0.2834490220270683, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0030414084396847606}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_recall": 0.2715933334719839, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002848612162614692}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_fmeasure": 0.26534001970520577, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0025743732024496244}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_precision": 0.13405990343107269, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0017363915410273162}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_recall": 0.12632320690490031, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001580690379939971}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_fmeasure": 0.12416901504237551, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0014418832805010986}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_precision": 0.22739524397837393, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002045754856820925}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_recall": 0.21790717317346972, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001977682176352203}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_fmeasure": 0.21281653093345984, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016678452099069705}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_precision": 0.24440894566677487, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0025218643599198604}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_recall": 0.23358308890323742, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0023681355345237325}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_fmeasure": 0.2284401060917875, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0021061890580456274}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.json new file mode 100644 index 0000000000000000000000000000000000000000..62851d54929460e9fba0182f92abcf1a760bedc7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "bleu": 6.8137963757639595, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.20255562203924876}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_precision": 0.3270546311530774, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0033260484118045196}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_recall": 0.30290304692810277, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0029793997242539795}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_fmeasure": 0.29832265261949864, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002682363598114479}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_precision": 0.146059799869631, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0019394392606377293}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_recall": 0.13509651368601627, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017660311848326784}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_fmeasure": 0.1327243773594466, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016010342153913112}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_precision": 0.25289429854529516, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0023232203307966158}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_recall": 0.23497554580132518, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002126463940220678}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_fmeasure": 0.23091319790847228, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001809456729054163}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_precision": 0.2773139281135476, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002808432208536525}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_recall": 0.2565055228473518, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0025015169643640652}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_fmeasure": 0.2526729166449464, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0022317763780196186}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.json new file mode 100644 index 0000000000000000000000000000000000000000..899b01e66690c99c9f7a620afb89443bab932fb8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "bleu": 7.341198614648136, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.17045073548615564}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_precision": 0.35350382405858616, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003442922432389858}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_recall": 0.3188764804549842, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0029638694103824277}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_fmeasure": 0.31596377144440585, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0026655508139599173}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_precision": 0.1549567262980173, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002127947989131943}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_recall": 0.13893389284637747, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018236049827216453}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_fmeasure": 0.13722355902976058, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016747877599416919}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_precision": 0.26952618807409345, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002533331450712522}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_recall": 0.24417509331372464, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002199216476423094}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_fmeasure": 0.2408545283139996, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018742380511928072}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_precision": 0.2985654514117335, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029755296285733485}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_recall": 0.2693279956215855, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0025433959718711577}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_fmeasure": 0.26664577905196357, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0022767260952207273}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.json new file mode 100644 index 0000000000000000000000000000000000000000..38ae2954b3a1209cc300d652a2a801ab24b6b1f7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "bleu": 7.664142184014725, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.18311227507126876}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_precision": 0.3746709568888028, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0034292359840454125}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_recall": 0.3318290086834598, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0028931410590327202}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge1_fmeasure": 0.3315310557370324, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002595366438750264}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_precision": 0.16260171493807835, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002161100502458248}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_recall": 0.14326943676270018, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018229254941988782}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rouge2_fmeasure": 0.14239753185765971, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016696513011695726}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_precision": 0.2835816428192323, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0025993635120059306}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_recall": 0.251337772350117, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0021560416701979584}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeL_fmeasure": 0.25032287278156323, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018610404732014262}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_precision": 0.31567282011474695, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0030093908891570794}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_recall": 0.2786749264473846, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0024797369016044467}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_gramatically_correct_text", "rougeLsum_fmeasure": 0.27861256778529525, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "0f54b6e2-42c0-45ec-8ea2-2e6204388f76", "prompt_jinja": "Combine all of the following data into a concise and grammatically correct text:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\n||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0022359749139328443}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.json new file mode 100644 index 0000000000000000000000000000000000000000..850fec7576db98401f1b06b15be539555b3374ee --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 0.11176674048639335, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.025745526624568513}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.16696437758477956, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017859239587553095}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.15714888553652667, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0014080404762761625}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.15222302512937821, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0013013498465447167}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.009953161364593704, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00045153060703839287}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.011372231163400725, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00047796121503254033}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.010123335458248412, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00043360666103113316}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.12080392040996726, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001200893081884765}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.11779742301789177, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0011408283583082188}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.11199161031913281, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0009318642813866649}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.15176134198199345, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015534141731862994}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.14365210992596641, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0012440730468959943}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.13868103668142837, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0011150022939164787}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.json new file mode 100644 index 0000000000000000000000000000000000000000..7c006bec6345fb2c576dbfcf2c916dd6114a40aa --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 5.3012905706855715, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06983249125236993}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.3815413917530348, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002837174970345969}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3064552216042878, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0023886076473393645}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.32162747895375954, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020771074301500782}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.13086483275629, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0020280885765991885}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.1025349516561498, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001571669556321608}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.10817189459012165, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015550558960603117}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.27916128217581454, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0023638984947284046}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.2222943424941319, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0018853089294649107}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.23379701509505144, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016853591821340379}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3136019413612245, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002623636065057541}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2503472789320967, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002117352162606577}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.26334461160376826, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019172374126938273}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.json new file mode 100644 index 0000000000000000000000000000000000000000..03fddbe9bfc97fa06fa924c5f4df01ad06678f3b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 6.484621213756497, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0974863563868723}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.41139978305209435, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003067700206274608}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3252856106278531, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024570831951622046}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3420522066441051, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020985317696014232}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.16044952433810813, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022415019504744573}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.12295995789487724, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016908155548698506}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.12966947477583363, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016114647269419636}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3101968039122714, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0026559494676439695}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.2432211605884282, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0020134767570951996}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.25601590775495564, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017579676075034684}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.34330225686796983, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002884969316299285}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.26983375724985587, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002240579967780497}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2842749213664702, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001992190307244928}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a846c628e4d5af3fc1ffe39d126f86b23c158a37 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 6.879629327338769, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1346069600960464}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.42201728977513014, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003107151077288339}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3272628452554048, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002461890669832865}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3463166802954874, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00213652320528259}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.17146778036168178, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0023302870066652893}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.12891634697023943, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017367276208110785}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.13691320451323, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016811203463266734}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3213628033975934, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027392401350909996}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.24620580859495172, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001997741786107464}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.2610757008973968, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017801310756353193}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3548763955773087, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029163728160237273}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2732798481620792, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022332299942385615}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2896766488362631, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001994600250845987}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.json new file mode 100644 index 0000000000000000000000000000000000000000..802c596fcef4a8a4b33c2c4c33dfaa542e323463 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 7.043340928793498, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.17457577578396632}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.42849398140403416, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003154039113080988}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3260253265844876, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024300314619900886}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3484130556989747, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021567720832225755}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.1755199620636604, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002326078614960514}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.12942494945873848, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017198177455500956}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.13896898011991943, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001696565627297103}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3295172578321846, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027851684130843772}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.24845018656704826, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002015612153914146}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.26571281983219025, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018278399179337257}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3613892288819798, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003004023862876739}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2729143969722366, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022213221391673625}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2923263218516018, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0020524443622954285}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4ad8203d1e99ed4082ad9eb8c723f1c34defa71c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 7.319824182452319, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.10193025707807249}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.44030532087327506, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031770242292659683}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.32784942801165234, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0023757237014025534}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.353385644913835, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020821634201849126}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.18788682322290728, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002464730672599637}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.13467537191827086, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001690154302772729}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.14603196173656227, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016877020428632365}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3410417220866126, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0028515279745281513}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.25124499237542, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001976384646702889}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.27131741619623057, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017940658157043932}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3732999668515814, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003040944777908066}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.27656091589535414, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002210511819363925}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.298421172979648, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0020128816004845508}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_0.json new file mode 100644 index 0000000000000000000000000000000000000000..06a3456693011865aa4329227619d7d608b37b6e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "bleu": 2.312044583390139, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0395109885826077}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_precision": 0.1483234108399301, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018820269691433504}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_recall": 0.2665312132559497, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0022782588706576823}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_fmeasure": 0.18396830789775534, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0019217889423799447}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_precision": 0.06330225911047903, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000929977214652403}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_recall": 0.1144099347030503, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0013911841551972658}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_fmeasure": 0.07857762779721571, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0010324442678352934}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_precision": 0.13168588320305488, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0014088056357095735}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_recall": 0.24187944010259957, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001991719734240969}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_fmeasure": 0.16491978865694182, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0015173618055678087}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_precision": 0.13170067737530292, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001562161536791986}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_recall": 0.2380165156086324, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0020441457742624673}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_fmeasure": 0.16382995952828802, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016389684965023624}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_1.json new file mode 100644 index 0000000000000000000000000000000000000000..abb6589d5f4ecae658adc9dad07b63ab8a5be576 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "bleu": 5.658373765079044, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08499855577351746}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_precision": 0.3785635846368343, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0030612871591419147}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_recall": 0.30450164969564714, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0022564011527415394}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_fmeasure": 0.31664965729123945, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020607356438432697}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_precision": 0.13934496500807864, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00216195315567069}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_recall": 0.10702848594772853, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0014968393936312507}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_fmeasure": 0.11238103667987336, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015100568087131015}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_precision": 0.28631430972883853, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002617927639070605}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_recall": 0.2283811920065958, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0018138508581349217}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_fmeasure": 0.2374686347495831, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016753126850071298}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_precision": 0.31633107781620623, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0028315570567799433}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_recall": 0.25293146488273016, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0020207172248228092}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_fmeasure": 0.2632560786781301, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018894463768983068}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_2.json new file mode 100644 index 0000000000000000000000000000000000000000..4fffa556b1bafe51c12b8e19b4b393025877db91 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "bleu": 6.917215486681154, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09030336208671559}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_precision": 0.40102908401240517, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031305165635581666}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_recall": 0.3245770394369534, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002380280848054982}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_fmeasure": 0.3365847325089085, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021240478562747096}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_precision": 0.1624015628216895, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022128114021614867}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_recall": 0.12717184459111075, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016440230921468948}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_fmeasure": 0.13240317910861094, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001585927980196938}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_precision": 0.3078746669304236, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0026746765410402343}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_recall": 0.24821866410165572, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001975259655202282}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_fmeasure": 0.25697032555307603, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017681623995959028}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_precision": 0.3384966177161513, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002883629760587024}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_recall": 0.27305479728579, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021713449800655122}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_fmeasure": 0.28336588654052414, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019832801111781904}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_3.json new file mode 100644 index 0000000000000000000000000000000000000000..5a460d7230a0a5ea4757d0f7cb42b1693ea01719 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "bleu": 7.302933244369964, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1527151661282377}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_precision": 0.40976641043825285, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003078900083587585}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_recall": 0.3298207802659436, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002370269980991039}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_fmeasure": 0.34292801400129946, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020983362895782443}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_precision": 0.16923415682313503, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022309657925827548}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_recall": 0.13169306775839348, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016574071058421535}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_fmeasure": 0.1375143860984762, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001597502116017482}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_precision": 0.31910429949813013, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00271697238304695}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_recall": 0.25477988953379643, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001954868697916928}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_fmeasure": 0.26487498731759745, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017575023861850282}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_precision": 0.35002435680776456, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002909025689835447}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_recall": 0.27988532121673076, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002164775670324916}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_fmeasure": 0.2914768408781806, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019710026406425415}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_4.json new file mode 100644 index 0000000000000000000000000000000000000000..26533aac829ea61d63f6cff24312aef50c9a514b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "bleu": 7.669963629530005, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.19346868748686652}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_precision": 0.41822864707123897, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031091354286543996}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_recall": 0.3361316604502726, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0023559546948861898}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_fmeasure": 0.34959289046921094, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020793186867037474}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_precision": 0.1737722798289324, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022559830525788267}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_recall": 0.13630282002247948, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001690717470047277}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_fmeasure": 0.14197862193928545, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001637642338037844}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_precision": 0.32559296595574067, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.00272622024383481}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_recall": 0.260656215712442, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019981009630238747}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_fmeasure": 0.270791556407417, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017960817490802496}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_precision": 0.3561490228639673, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002943695124328949}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_recall": 0.28548991550740394, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022090994833757244}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_fmeasure": 0.29703338834518844, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002014348371578559}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2bd81bfd2a8ad6b0506a1c1cc9ccc7d8a65e165a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_e2e_nlg_cleaned_text_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "bleu": 7.654080416990873, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.19571238370874128}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_precision": 0.4239353949486354, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031328799053710198}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_recall": 0.3346884409831521, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00232049776848557}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge1_fmeasure": 0.35023251954607215, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002029722816220765}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_precision": 0.17998608899131224, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022646779528023306}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_recall": 0.1379401661329551, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016637853565731088}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rouge2_fmeasure": 0.14479391497677302, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016055061136987026}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_precision": 0.33239544579609576, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002774448505172659}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_recall": 0.2607705965299782, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001964723134792992}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeL_fmeasure": 0.2728400159017183, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017573515029372963}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_precision": 0.36254724652343057, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029613989798622157}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_recall": 0.28517595951447855, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0021666326647344194}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "text", "rougeLsum_fmeasure": 0.29856008882369317, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "cdecbb5a-d3e8-46f3-9ea8-22025bc59e3b", "prompt_jinja": "Information: {{meaning_representation}}\\nDescription: ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001949304832193815}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c2d9d95b94cd03ef8b06fa2cab9657f97792963a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_precision": 0.08601322052693357, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001489727730411717}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_recall": 0.20924410822933326, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0034231335371689518}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_fmeasure": 0.12035436857080709, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020099353839720534}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_precision": 0.01193354789546424, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0006397142671079087}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_recall": 0.029994300661093865, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001603282064351233}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_fmeasure": 0.016871170959750856, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0008961563503630702}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_precision": 0.07594233748050107, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001192403250385716}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_recall": 0.1855080583745368, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002795393404522018}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_fmeasure": 0.10635833102686837, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016094140448635636}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_precision": 0.06979928841705295, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0012075993866203928}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_recall": 0.17170883890703695, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0029043246785420388}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_fmeasure": 0.09800348259551175, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016526422289216889}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "bleu": 0.5989061497441678, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.04560411376477311}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b1f2f82912cefb400029fbba876dce290b7b9954 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_precision": 0.11774017314240483, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019052567574435065}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_recall": 0.21726972418847335, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004161648851245577}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_fmeasure": 0.14265747670098736, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022533103077694763}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_precision": 0.012105474988350063, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000710088400602416}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_recall": 0.026644819771942975, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001646589314669167}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_fmeasure": 0.015898317357067135, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009292567523827307}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_precision": 0.08871947393016015, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0014307460077157546}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_recall": 0.16050680730614136, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0029158160901583295}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_fmeasure": 0.10633984941798981, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0015849974450020952}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_precision": 0.09440999098393471, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015075483157921815}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_recall": 0.1745714923938198, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0033720794167318327}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_fmeasure": 0.11432471005231339, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017839300909078509}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "bleu": 0.8307325092609459, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08101919299614214}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0e90e918a4884d2cc7d7dcfb2bbb0c419992d078 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_precision": 0.11302706654940622, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018593332628316893}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_recall": 0.2460436363471978, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0037872620423532104}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_fmeasure": 0.1481415675239767, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021642331088208224}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_precision": 0.013053642716381332, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007155352294008017}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_recall": 0.03017269382059932, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015996985516903391}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_fmeasure": 0.0174749223761466, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000900127336792311}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_precision": 0.08299048940700292, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0014081479474376902}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_recall": 0.17954598888703394, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0026498882602493264}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_fmeasure": 0.1080255694309031, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0014919817019001394}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_precision": 0.08995434230427667, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015144673716852113}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_recall": 0.19646935910004223, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0030868956085950226}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_fmeasure": 0.11778050548494788, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017160843639228713}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "bleu": 0.7096901242580976, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05577067558873664}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a4bde6facecee1cbd7d5b8ec26609e3a0a42e9da --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_precision": 0.10499197275901183, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019010472325354404}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_recall": 0.23424489218202285, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004151663117206758}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_fmeasure": 0.13993184120346575, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002395620259341809}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_precision": 0.013013272243975858, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007437340426547505}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_recall": 0.030512183916105506, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016971799846190242}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_fmeasure": 0.01773853594640338, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009780501520640062}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_precision": 0.07787068629627976, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013947978353617287}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_recall": 0.17322899854212984, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0029625614134759564}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_fmeasure": 0.10336085541455355, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016861984554507592}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_precision": 0.08385124269644273, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015454338092998716}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_recall": 0.1877925759738355, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0034402617687262706}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_fmeasure": 0.11170901074459809, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001935231182288914}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "bleu": 0.7643563196224507, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.060516055001859886}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8f7b02e20c06188359b9681ad718d76b2de4159e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_precision": 0.029270950352660315, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0020065508927545363}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_recall": 0.054292494387326445, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0035095105726254796}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_fmeasure": 0.034205133663320925, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002130522101860963}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_precision": 0.004080736859560897, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0005900878496520041}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_recall": 0.007641895050367479, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00097223815465809}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_fmeasure": 0.004783264838725394, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006044566237329345}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_precision": 0.022370274339247025, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001625959107979613}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_recall": 0.04008109112128974, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0025643726913754435}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_fmeasure": 0.025477711600550405, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0015794541340020175}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_precision": 0.023817663907487817, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017123315453502917}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_recall": 0.04362025506139685, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002869716532881049}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_fmeasure": 0.027411630968536074, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017286334063830189}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "bleu": 0.29936737554664894, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06333594224392126}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4a57e3075b74446f22664f90e214737931d1405f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_precision": 0.0008576329331046312, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0008576329331046343}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_recall": 3.1764182707578934e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 3.176418270757912e-05}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge1_fmeasure": 6.125949522175937e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 6.125949522176127e-05}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_precision": 0.0, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_recall": 0.0, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rouge2_fmeasure": 0.0, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_precision": 0.0008576329331046312, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0008576329331046343}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_recall": 3.1764182707578934e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 3.176418270757912e-05}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeL_fmeasure": 6.125949522175937e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 6.125949522176127e-05}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_precision": 0.0008576329331046312, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0008576329331046343}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_recall": 3.1764182707578934e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 3.176418270757912e-05}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "rougeLsum_fmeasure": 6.125949522175937e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 6.125949522176127e-05}, {"task_name": "gem_xsum", "prompt_name": "DOC_boils_down_to_simple_idea_that", "bleu": 0.0, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "2b9c75ca-2848-4a63-b3ce-b86ea2e2d7e8", "prompt_jinja": "{{document}}\nThis boils down to the simple idea that ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_0.json new file mode 100644 index 0000000000000000000000000000000000000000..1b2de554b133834115b97cff74bb58e6dbb3ee79 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_precision": 0.08785520812835405, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017998077566166923}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_recall": 0.21381700588328337, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004102874678024494}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_fmeasure": 0.12304686221145984, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0024384970755190246}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_precision": 0.01396692872396121, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007089258908322197}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_recall": 0.03497812070098322, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017422549858707552}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_fmeasure": 0.019716305531943378, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009850886667063586}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_precision": 0.073836479271441, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013755441288147774}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_recall": 0.1810860810587385, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0032222426550226036}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_fmeasure": 0.103624513733133, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018723555859277226}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_precision": 0.06797287037657533, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014074123866873501}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_recall": 0.16720206816344646, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0033103712098051024}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_fmeasure": 0.0954563322396712, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019181008675671265}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "bleu": 0.6951449410126411, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07649685778024824}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_1.json new file mode 100644 index 0000000000000000000000000000000000000000..71646ad510cd61bbb8e516e43acf63419217ded6 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_precision": 0.12486307177941995, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002333030764269263}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_recall": 0.17701443524540267, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0035983361097093195}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_fmeasure": 0.13551729087860911, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002244723695600438}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_precision": 0.01080484683339422, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008615061540764822}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_recall": 0.01766476395873732, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001206171246859144}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_fmeasure": 0.012104885502617603, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0008081822477551506}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_precision": 0.0970099571674389, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017837861435037988}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_recall": 0.135913907810521, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002573537485904688}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_fmeasure": 0.10464228517330777, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016250083581085943}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_precision": 0.09870668722966038, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001839221923939297}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_recall": 0.13939382706838868, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002824716995864924}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_fmeasure": 0.10680811423589318, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0017423671645419993}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "bleu": 0.6418362037219415, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.10975824216647798}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2e98ac5af86588fe521650c53c610e3bc4e642b4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_precision": 0.13693727131284883, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002867447164210865}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_recall": 0.1925058409582237, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00344213336972596}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_fmeasure": 0.14570650267756477, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002378941385995561}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_precision": 0.015417250842210722, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001067355594423882}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_recall": 0.02339412063589744, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015128675685687942}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_fmeasure": 0.016540998688253494, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0010166295676320167}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_precision": 0.1092349946394738, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0022921046872309246}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_recall": 0.15434494177372146, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0026589145886085404}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_fmeasure": 0.11612824174493956, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018217319112931597}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_precision": 0.10856158470399667, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0023269612772477415}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_recall": 0.152553343173584, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0027788394482328844}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_fmeasure": 0.11514154801275071, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018878468117351512}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "bleu": 0.8108179139657711, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.12705995346927912}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_3.json new file mode 100644 index 0000000000000000000000000000000000000000..29b3096652f86fc44d1351846192647de5832393 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_precision": 0.13563786026465277, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0030566129634817477}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_recall": 0.18802799291524244, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00357664038215709}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_fmeasure": 0.1426531931541618, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002586850906713085}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_precision": 0.017442792260430814, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001100826746094403}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_recall": 0.026449724957200424, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015566681933243279}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_fmeasure": 0.01889574180325777, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0010911361599695013}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_precision": 0.1079022009981362, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002335404534765411}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_recall": 0.15167890991580765, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0028008093319595393}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_fmeasure": 0.1139215911001409, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0019571989970646572}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_precision": 0.10782682350987516, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0024013803164332965}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_recall": 0.15026311614000185, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0028973161396880012}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_fmeasure": 0.11339280362226653, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0020325791985732135}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "bleu": 0.8773649045212694, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11660132941903724}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_4.json new file mode 100644 index 0000000000000000000000000000000000000000..5fb62289a4135676e75a9bd629a94ca6b0c5bfd7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_precision": 0.04056265174869925, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0027356110529654534}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_recall": 0.050786036823568484, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003196010331614339}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_fmeasure": 0.040147604598473816, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002480690262574129}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_precision": 0.006607559048731122, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001009742810903406}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_recall": 0.00849924754298773, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0010791020860047476}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_fmeasure": 0.006640579605150196, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009022022003023071}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_precision": 0.03310929259525501, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.002243362243706627}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_recall": 0.04113526678175656, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002542893900861329}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_fmeasure": 0.032413930700901525, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0019512957708450456}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_precision": 0.033227844625563996, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0022608759002654445}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_recall": 0.04106024416303349, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0025628565510947927}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_fmeasure": 0.032497622810383237, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001977165308187117}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "bleu": 0.22273027127435427, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.053862193531175}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4b8a99421e3ca4af5baff820bebdf90dc81e931c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_DOC_tldr_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_precision": 0.0028264204041118578, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0008349091404664074}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_recall": 0.002169808352873373, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0006083551170636029}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge1_fmeasure": 0.002408518357660293, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006851091594038417}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_precision": 0.00029254180891250816, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00015725543023099734}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_recall": 0.00020462820860040322, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00011211479804596237}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rouge2_fmeasure": 0.0002397463551736582, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00013033009573483993}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_precision": 0.0020221693154545543, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005384638968072176}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_recall": 0.0016282149852303604, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0004451035213829608}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeL_fmeasure": 0.0017660754927783585, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00047012290492895134}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_precision": 0.00218432680280627, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0006054710624941614}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_recall": 0.001726345399206282, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00047538249577709987}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "rougeLsum_fmeasure": 0.0018882985436314338, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0005141685685603013}, {"task_name": "gem_xsum", "prompt_name": "DOC_tldr", "bleu": 1.1827594679031042e-43, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "db54e9b5-8ca9-4266-a773-695a3dc5bbf4", "prompt_jinja": "{{document}}\n\nTL;DR: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 4.377910669778258e-37}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e09b94eb031b84c78bc695a1f8df95c1a9c45a28 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.1158071847580149, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018165761216020508}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.28067020528577075, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004128869715644845}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.1620070178287433, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002441688281448867}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.019660583386168388, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000745126629124706}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.04960567998718761, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0019206822821280743}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.02780910006627101, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001048269259419271}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.08983266681131948, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012376193912151856}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.21960260688104757, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0029450533082012067}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.1259092579196459, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016674239611603732}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.09018130758669934, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001441468599655175}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.22079158054359857, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0034244847154332263}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.1264703650002751, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019559064654329516}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.9867298890552224, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0636863740857457}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..a0373d1c0609243d1fceba383455cffbaa0712df --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.12534579534327125, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.00193945618548172}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.27058957289695346, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0043828330597585445}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.16460140030448664, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0024490418088823833}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.01759280829959392, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008355125639125885}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.04185140008866747, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0019643064430206994}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.024161160413064688, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011266352477578854}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.09368708847755541, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013943909386695036}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.2019168442700265, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003109796908751444}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.12258268240644458, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016862279472992232}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.09878883028828475, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015789128996359261}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.21398695995793088, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003606717868964285}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.12964372208686004, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019843558414494125}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.986334549008572, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1026134280695105}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1e77b7c5b33ef0618a653e98fe617b288e26156a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.11833601279755995, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002199294284784323}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.24121068192166684, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004044710436865143}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.15079272411614866, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0024454125650679305}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.016827094361182786, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008831709899277623}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.036633244517976074, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018506466619519948}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.021955967558594934, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001087239850414522}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.09217477971271017, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0016246776666746755}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.18812387120682225, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002891644059806244}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.11723212187021603, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001714077795522329}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.09310810494075238, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001750123872504354}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.1906145778565124, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00328348190414569}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.1185738466895609, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019372106823996678}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.8510392504395363, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06647941816704432}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..15316ae57d4b435164309c6de2cc26d6dd227db5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.11511064720378139, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0024031770641084484}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.22827150593652096, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.00416286720206103}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.14375568998105198, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002550732075823139}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.016386126450038938, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009430306754946043}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.03453203803155488, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018851772654117098}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.020853724585447975, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011315789722664176}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.09095045508362522, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0018411782290517719}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.18142579882700435, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0031425768784492493}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.11360197423806047, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001884854751254693}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.09156035684290141, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.00196609095636847}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.18238021901307033, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0034503657802804075}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.11426161274403947, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002072690651007159}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.8650437116316979, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08348862368049724}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..03ccc2ffb11ba52b45aaf17c59e47aca72df9242 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.0361602458825991, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0025988245241512615}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.0581275939105786, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0035711432213003467}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.03860671254711545, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022900584510195322}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.005992076983678361, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011155187418557422}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.009962165254990031, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0011307954713829275}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.006231843463345877, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007012509924568781}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.03038144486746073, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0023281897845746865}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.04731308569695526, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0028495942670980546}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.031530683354832556, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018296711578288528}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.030582547849958886, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002360088780868479}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.047711987788717505, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002969080473622203}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.03178346574583942, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001898518321849197}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.41795248569633103, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.084171862077561}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..11fe3bc3eca8425566827b97758dacdecaa488c7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.00282366128721056, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0007697832157484954}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.002365813329267624, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0006488826359222657}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.002527603190035361, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00068757084609251}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.000252945660825794, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0001130835622425815}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.0001820087669144273, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 8.275145912995973e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.00020969228861543636, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 9.41768743666813e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0020324491777993737, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0005401952082914505}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.001705553553343957, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00045030351383285445}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.0018180833551753694, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0004787735421768299}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.002125879390906554, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0005641336556569049}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.0017893614930695643, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0004747147768544628}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.0019064161369800514, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0005036949386606113}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 8.059349929930117e-40, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 3.4078462014416495e-34}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_0.json new file mode 100644 index 0000000000000000000000000000000000000000..71b35d2c428af74aec9b85d5b426772cb82a2498 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_precision": 0.09959661209849045, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001720794675352159}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_recall": 0.24296043524964275, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003922924238883301}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_fmeasure": 0.1394877149729816, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0023191928763038917}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_precision": 0.015676753241847172, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000696440808966843}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_recall": 0.03949985958379005, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001763700865011535}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_fmeasure": 0.02216490573223825, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0009754645017508243}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_precision": 0.08380837589550291, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012762456181644143}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_recall": 0.20538014455763795, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002967340337812102}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_fmeasure": 0.11748646473161478, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017149795760748592}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_precision": 0.07649621759728135, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013213921725338553}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_recall": 0.18872305812070983, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0031571885489383726}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_fmeasure": 0.10747916740229993, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018034915409559326}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "bleu": 0.7657539744351544, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.05960388643906178}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_1.json new file mode 100644 index 0000000000000000000000000000000000000000..65491d03bf852793ad8bed0b939e648562829eac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_precision": 0.10779079125778714, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017364689097811245}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_recall": 0.2531343205060018, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003849102811710255}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_fmeasure": 0.14786528609926117, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022472583600236513}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_precision": 0.01717373699792966, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008086755123805268}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_recall": 0.04258571346118677, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001990619230673135}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_fmeasure": 0.024050432775105567, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011119514244593799}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_precision": 0.08616745994892451, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012884289488737097}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_recall": 0.20370042941588284, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002916372748330544}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_fmeasure": 0.11829636533500087, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001646799217950579}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_precision": 0.08416622990633002, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014043090246987175}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_recall": 0.1990339703496491, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0031810082266012984}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_fmeasure": 0.11550772215317513, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018112100752252266}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "bleu": 0.9744864699598849, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0715803104250675}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f1568b8e09eb6bd08ca9f05780ee96212f71a275 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_precision": 0.09974253383196298, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0016508496308147503}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_recall": 0.24044895366223354, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003610084224116856}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_fmeasure": 0.13806182767970213, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021135695098749214}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_precision": 0.015474430089813513, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000760295961817625}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_recall": 0.0390759843386084, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0019080665242204116}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_fmeasure": 0.021850132907452764, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001062000791042869}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_precision": 0.08367374656252795, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012812689380292408}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_recall": 0.20304267063542045, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0028755638811545294}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_fmeasure": 0.11603612234525328, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016404618326966145}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_precision": 0.07733059958801149, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013169092247786304}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_recall": 0.1882421408340462, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0029988980863709493}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_fmeasure": 0.10727262095783592, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016997810733515313}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "bleu": 0.8347136741256534, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.062076277683922425}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_3.json new file mode 100644 index 0000000000000000000000000000000000000000..decd3d954e01f014d7261c92d5172d141f303709 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_precision": 0.09689033249970055, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018810183346657067}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_recall": 0.2240723175463038, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003898850764408054}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_fmeasure": 0.13115011437349358, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002301574585288779}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_precision": 0.014805074825435426, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007813933511829814}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_recall": 0.035775335550481645, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018150201824477363}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_fmeasure": 0.020384730084258812, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001038756802634804}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_precision": 0.08180231716848364, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001509999290109991}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_recall": 0.19020520762940066, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003130840716495653}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_fmeasure": 0.11089421988144217, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018199727364072546}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_precision": 0.07516233715156442, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014943501606461884}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_recall": 0.17573853870134074, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0031552844726888797}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_fmeasure": 0.10193009295990486, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018015834348326844}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "bleu": 0.8124291106760078, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07588482930693484}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_4.json new file mode 100644 index 0000000000000000000000000000000000000000..64221bb41541de4b69bc7403a35f22d94b87b6d7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_precision": 0.03575664714500481, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0024098528232116526}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_recall": 0.060819442484463054, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003534881031726274}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_fmeasure": 0.03985059812853305, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022760105727489804}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_precision": 0.005750259558436412, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0006358449659266129}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_recall": 0.011282915311051312, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0011299755593093203}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_fmeasure": 0.007018029042731219, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.000685007347774824}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_precision": 0.030116615236100916, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0021214097977901845}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_recall": 0.05019883302718781, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0028798226137028322}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_fmeasure": 0.032959125867263926, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001860506762679618}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_precision": 0.02960913737630851, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0021194541107393936}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_recall": 0.049340056932530726, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0029147509307593054}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_fmeasure": 0.032337968793062846, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018663100809540166}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "bleu": 0.5188346596881508, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1162647822321323}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_5.json new file mode 100644 index 0000000000000000000000000000000000000000..db875de6ac3db7445b92eb413f61957f1bc8469f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_DOC_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_precision": 0.0027970449110702633, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0008129954674738013}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_recall": 0.0024652900122106723, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0007379988663176068}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge1_fmeasure": 0.00257629662639923, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0007584585077324427}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_precision": 0.000261704167087075, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00017583118303625035}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_recall": 0.00027915111155954665, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0001876136151566084}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rouge2_fmeasure": 0.00027004452530749476, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.00018148779778783585}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_precision": 0.002311528640826497, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0006531263217620076}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_recall": 0.0020110161874394208, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0005684052414990399}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeL_fmeasure": 0.002111652191363848, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0005941763033496732}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_precision": 0.002412426632956454, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0006907319147059392}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_recall": 0.002115676852444913, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0006160449658742334}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "rougeLsum_fmeasure": 0.002214671104382056, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0006380204218087325}, {"task_name": "gem_xsum", "prompt_name": "summarize_DOC", "bleu": 6.894559936640943e-38, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "019726f2-7140-4ab6-a18d-a5f9cc709a47", "prompt_jinja": "Summarize: {{document}} Summary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 5.078171225423703e-32}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..24b1144bf95164ef52c6bc7cb4d74b5cbead57d4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_precision": 0.10766417393148146, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0017247775348159335}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_recall": 0.26220045752079946, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003975340578476309}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_fmeasure": 0.15080495502999547, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0023292636824101256}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_precision": 0.018011700797613012, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007071056250652039}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_recall": 0.045671998488902174, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018504317904469703}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_fmeasure": 0.02550920276281168, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0010004591177405439}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_precision": 0.08803820960705872, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012435040927227102}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_recall": 0.21591728450361894, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0029447735431074496}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_fmeasure": 0.12351381489334008, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016767094669245285}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_precision": 0.08357513379135657, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0013517986553990002}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_recall": 0.20562438203051336, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00324355265235417}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_fmeasure": 0.11739126743954412, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018454058790702413}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "bleu": 0.9053200662535719, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08304303167521133}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..41906b810ba05e85731076bfb877a7501030248b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_precision": 0.12366225220702332, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019035992000767568}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_recall": 0.2746639885726219, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004363644416585785}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_fmeasure": 0.16458352372455684, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0024404180174069736}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_precision": 0.01831848136320181, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008613493134626757}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_recall": 0.044642681354896206, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0020693469381105048}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_fmeasure": 0.0254681124378878, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011760381453017}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_precision": 0.09283957435911433, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013633579746673554}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_recall": 0.20656882824913186, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0031972954373685456}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_fmeasure": 0.12335078113747294, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017240156359532798}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_precision": 0.09649134174288254, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015227636340121218}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_recall": 0.21532151284750878, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0035949140524341836}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_fmeasure": 0.12839142485622748, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019623450564247953}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "bleu": 1.0517549411798284, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08869197714127522}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0c677a563048023616842c815bc440e88fba576b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_precision": 0.11477590393567126, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002116330005854684}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_recall": 0.24394235435709302, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004069202937893897}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_fmeasure": 0.1489043126868222, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002414057619883924}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_precision": 0.017617469606827755, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009209461630191176}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_recall": 0.039942432060720914, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0020431563227289234}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_fmeasure": 0.02344635398091455, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011875761392866745}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_precision": 0.09141125984419861, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0016082349170530377}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_recall": 0.1955280825356397, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0030928571079126945}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_fmeasure": 0.11876289392440431, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017958651709665465}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_precision": 0.08991259226184872, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017045288942889236}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_recall": 0.1921527798348713, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003343896055475177}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_fmeasure": 0.11666161719412536, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019395954814823589}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "bleu": 0.9359180990331135, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.097313852367643}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..b76e0d1ccf7d2630b0ab03b59901ae92091b3813 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_precision": 0.10967477103152969, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002373361239237867}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_recall": 0.22921698427745044, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004179760492319134}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_fmeasure": 0.14143975183431184, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002624919098315165}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_precision": 0.01649113601256011, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009108210651028919}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_recall": 0.03621079704469094, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0019138662731944262}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_fmeasure": 0.021683379341115812, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011414403236527958}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_precision": 0.08842314517868648, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017879328745720076}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_recall": 0.18710793878265647, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003197890711089028}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_fmeasure": 0.11452190311765521, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0019555924223011788}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_precision": 0.08585520766581471, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018884567405713097}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_recall": 0.1806032948250851, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003410584937322093}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_fmeasure": 0.1108174940054984, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002093506046561213}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "bleu": 0.8545144299660299, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.08062058614293066}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8b614125fa2f438e014a5ebfa30806e5e901c70d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_precision": 0.033523252947635904, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002262808835339776}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_recall": 0.05524121400042497, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003532082798269108}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_fmeasure": 0.037197403374487924, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0022954634096379305}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_precision": 0.0051584458678752216, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0007026116069116543}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_recall": 0.009635922855585887, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0012421025115398562}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_fmeasure": 0.006054078203169595, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0007863768658417492}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_precision": 0.028324453021289078, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001994218364384606}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_recall": 0.045582045072611516, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0028859350433643343}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_fmeasure": 0.030859284839692826, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0019074776816356488}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_precision": 0.028190743604595166, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0020193479074785987}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_recall": 0.04530859399363896, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0029471761234043025}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_fmeasure": 0.030639007644487726, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019336596995026226}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "bleu": 0.41550983722811713, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11383336021662172}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef9edb552946db2f8451c8bf5704ff55822425a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_precision": 0.0031446540880503146, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0010851526656093654}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_recall": 0.0004018246904679879, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0001360401158331796}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge1_fmeasure": 0.000708246579679391, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.00023949778866834165}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_precision": 0.0004288164665523156, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0004288164665523165}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_recall": 2.858776443682104e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 2.8587764436821168e-05}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rouge2_fmeasure": 5.360205831903945e-05, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 5.3602058319039565e-05}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_precision": 0.0031446540880503146, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0010851526656093654}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_recall": 0.0004018246904679879, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0001360401158331796}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeL_fmeasure": 0.000708246579679391, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.00023949778866834165}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_precision": 0.0031446540880503146, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0010851526656093654}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_recall": 0.0004018246904679879, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0001360401158331796}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "rougeLsum_fmeasure": 0.000708246579679391, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00023949778866834165}, {"task_name": "gem_xsum", "prompt_name": "summarize_this_DOC_summary", "bleu": 0.0, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "7d3584c5-8864-4d11-bce9-65499cdef4cb", "prompt_jinja": "Summarize this document: {{document}}\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.0}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_0.json new file mode 100644 index 0000000000000000000000000000000000000000..8273222fad9d0566ac6f5c37a3db1fb275737f30 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "Correct the solution", "bleu": 5.044003528820165, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.22920626380593712}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_precision": 0.08223335503910409, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.0024516571009502493}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_recall": 0.6043317835131486, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.007310140932058555}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_fmeasure": 0.13070246265270175, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.003003328865094663}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_precision": 0.06021814295664582, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.002303597081892545}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_recall": 0.44232864311481884, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.008135472118435535}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_fmeasure": 0.09519041983155013, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.002905103095548517}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_precision": 0.07970090960055028, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.002390776645143582}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_recall": 0.5915829369519617, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.007434090945267709}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_fmeasure": 0.1270728154104261, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0029857125025585436}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_precision": 0.07898279807795379, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0024089195054829956}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_recall": 0.5841163781141749, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.00745835270564824}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_fmeasure": 0.125629974165267, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.002984884476068228}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_1.json new file mode 100644 index 0000000000000000000000000000000000000000..95c1e83b12f468607807223fed5c6d0b9ed684eb --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "Correct the solution", "bleu": 10.987284589298396, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.6228982805404496}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_precision": 0.3018921785857166, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.007592424912559347}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_recall": 0.34032411186465444, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.007665397277299667}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_fmeasure": 0.27365913419935356, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.007178789576035563}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_precision": 0.182995294256973, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.007121557687340213}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_recall": 0.2131172886544418, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0073735162438965775}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_fmeasure": 0.1734691615853129, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.006761885716826925}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_precision": 0.2866580016638699, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.007545348452121212}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_recall": 0.3272517692490847, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.007719965820540302}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_fmeasure": 0.2617978649064106, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.00719744805064835}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_precision": 0.29054400425577176, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.007575454546327207}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_recall": 0.3290770238121191, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.007681543530250764}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_fmeasure": 0.26419466018780496, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.007189020162760364}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_2.json new file mode 100644 index 0000000000000000000000000000000000000000..607c10f2330046ac8bdb4a0fdef9f7c11ec29005 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "Correct the solution", "bleu": 13.894511213158287, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.8739525580726594}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_precision": 0.3962235671288584, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.008329795251643627}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_recall": 0.44796823076786213, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.008022473299790518}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_fmeasure": 0.3674980198284435, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.00787898395002465}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_precision": 0.27084269853025533, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.008065996347205293}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_recall": 0.31137177426270085, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.008133141525352511}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_fmeasure": 0.25734856308354354, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.0076839950683234475}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_precision": 0.37925499641508387, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.00832851687783064}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_recall": 0.4342613524811934, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.008157597971122069}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_fmeasure": 0.3543621394489363, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.007955653293849538}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_precision": 0.3822857138351711, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.008360452943863943}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_recall": 0.4342525578898354, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.008116059673105629}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_fmeasure": 0.3559552758288509, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.007950933392077896}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_3.json new file mode 100644 index 0000000000000000000000000000000000000000..de8667e0a7b6f303e683f36759d494454307951d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "Correct the solution", "bleu": 16.302962969684817, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "bleu_stderr": 1.0914160471683245}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_precision": 0.44754150572005014, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.008508724146964648}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_recall": 0.4928656980785378, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.007959264981992405}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_fmeasure": 0.4159209145067388, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.008066180840731338}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_precision": 0.31950165407284764, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.008430696030852732}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_recall": 0.35405055947121816, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.008289900831830925}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_fmeasure": 0.30169097752148116, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.008003118328318673}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_precision": 0.4296491063999405, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.008545775185136658}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_recall": 0.47866238354613455, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.008119911722901458}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_fmeasure": 0.4021318671912827, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0081642603534126}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_precision": 0.43342040994924064, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.00856185501876351}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_recall": 0.47874998363575016, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.008081456218781254}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_fmeasure": 0.4041172336659238, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.008150961646219602}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_4.json new file mode 100644 index 0000000000000000000000000000000000000000..90ab0a6c9adb4f73c9d5039b6f6f1817b7a0e959 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "Correct the solution", "bleu": 18.29568798498642, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.8400045952338919}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_precision": 0.47003616790222097, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.008492394610500243}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_recall": 0.5070618235168789, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.008034196403817398}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_fmeasure": 0.440913771806968, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.008161084155097175}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_precision": 0.34267924080360035, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.00849291013938346}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_recall": 0.3721650196784438, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.008345501652871087}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_fmeasure": 0.32589784419427137, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.008140627546699501}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_precision": 0.4545619116360723, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.008535490921376865}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_recall": 0.49441236285200274, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.008175372919559136}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_fmeasure": 0.42864556356106626, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.00825295711841848}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_precision": 0.4575870105061546, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.008542975114188618}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_recall": 0.4951955460109368, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.008149833461155942}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_fmeasure": 0.430525903474684, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.008241357230569303}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_5.json new file mode 100644 index 0000000000000000000000000000000000000000..49382707fe7aacb677e2f802cb5695dd351e9a5e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_Correct-the-solution_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "Correct the solution", "bleu": 19.563665938000955, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.830837212255332}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_precision": 0.4850213774986562, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.008412810347685195}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_recall": 0.5175895233206349, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.007925276186417592}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge1_fmeasure": 0.45358632651135367, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.008079574036676742}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_precision": 0.35233139121336177, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.008496659674238034}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_recall": 0.37841523275236855, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.008335884723129022}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rouge2_fmeasure": 0.33520179328257893, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.008136267592204509}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_precision": 0.46894629707993607, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.008460443723532397}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_recall": 0.5041604671316591, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.008082489163576902}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeL_fmeasure": 0.44099249707631255, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.00818874543924558}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_precision": 0.4720370238207721, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.008475086337406505}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_recall": 0.5048483591695989, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.008038036370329855}, {"task_name": "piqa", "prompt_name": "Correct the solution", "rougeLsum_fmeasure": 0.442736079453689, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "5f4b4645-9438-4375-9062-083130e6d04e", "prompt_jinja": "Given a goal and a wrong solution, rewrite it to give a correct solution.\nGoal: {{goal}} \nSolution: {{[sol1, sol2][1 - label]}}\nCorrected solution:\n|||\n{{[sol1, sol2][label]}}\n", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.008170530134058251}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d2b4a8f953916e48a15fc461a333319a49377589 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc": 0.49075081610446136, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011663828032649183}, {"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc_norm": 0.49075081610446136, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011663828032649183}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.json new file mode 100644 index 0000000000000000000000000000000000000000..146ec6103facaa8b97e8e16f17fad6fc3451674a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc": 0.5021762785636561, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011665713661738877}, {"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc_norm": 0.5021762785636561, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011665713661738877}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.json new file mode 100644 index 0000000000000000000000000000000000000000..b576a5cc9129704e905c835a84249611f210ceac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc": 0.5043525571273123, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011665382144642399}, {"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc_norm": 0.5043525571273123, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011665382144642399}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.json new file mode 100644 index 0000000000000000000000000000000000000000..79d2140003a1b9014c4737c7e7baffa1e32bee0e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc": 0.5016322089227421, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011665762007194866}, {"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc_norm": 0.5016322089227421, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011665762007194866}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.json new file mode 100644 index 0000000000000000000000000000000000000000..0c691fb8f69143debed380fafadfd26c3a1ea888 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc": 0.5048966267682263, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011665264730078137}, {"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc_norm": 0.5048966267682263, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011665264730078137}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.json new file mode 100644 index 0000000000000000000000000000000000000000..aa7642c08756830057adcd0ff1230c320be493d9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc": 0.514145810663765, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01166115447552484}, {"task_name": "piqa", "prompt_name": "choose the most appropriate solution", "acc_norm": 0.514145810663765, "fixed_answer_choice_list": ["Solution 1", "Solution 2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "adfef248-f856-44fa-affd-e3223718854e", "prompt_jinja": "Given a goal and 2 solutions, choose the most appropriate solution.\nGoal: {{goal}}\n- {{\"Solution 1\"}}: {{sol1}}\n- {{\"Solution 2\"}}: {{sol2}}\n\nAnswer by returning either {{\"Solution 1\"}} or {{\"Solution 2\"}}\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01166115447552484}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_0.json new file mode 100644 index 0000000000000000000000000000000000000000..5952b84db72cc8201c8fe91bda32c17cdd11e4df --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "no prompt needed", "bleu": 0.08644025412923256, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.009820950909340235}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_precision": 0.022663125514556327, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.0013513829670530827}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_recall": 0.1592144653136851, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.003449871907818082}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_fmeasure": 0.031036089835208214, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.0009813521147527423}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_precision": 0.003241010643234634, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.0004333769961243567}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_recall": 0.021524339394750014, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0013450358010657275}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_fmeasure": 0.004256247232539841, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.00034400170235730353}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_precision": 0.020762352004530072, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.0012497895941737545}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_recall": 0.1502718739661574, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.003305027485971818}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_fmeasure": 0.028702267430638435, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0009058455781743254}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_precision": 0.01933761544810985, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0012600611343390243}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_recall": 0.1362003183642396, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.00300408432276789}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_fmeasure": 0.025974232921307155, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.0008611143023707996}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b89cc3209249c5618d75ba1232f56c208146fa42 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "no prompt needed", "bleu": 0.14304039520961487, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.020196407881148105}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_precision": 0.053711187417481356, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.0029279067285896583}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_recall": 0.09582097083032212, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.00324411522349448}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_fmeasure": 0.04722334546545548, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.0020880436511264647}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_precision": 0.009321490289307479, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.000928495984049966}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_recall": 0.013837525790323843, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0011119759768626336}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_fmeasure": 0.007609013308850757, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.0006822487640430323}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_precision": 0.04649502848369309, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.00254016005961217}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_recall": 0.08725521239472234, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.0030082346793116844}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_fmeasure": 0.04129383170227979, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0018149259520630428}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_precision": 0.04637512898059172, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0025849567246808763}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_recall": 0.08219775751795474, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.0028538866420825446}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_fmeasure": 0.0403293623763229, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018133499923210787}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6fa6f518bacd1e036450714f98b6cd84a92a347a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "no prompt needed", "bleu": 0.2608651316164953, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.03978730347320043}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_precision": 0.05429344326618384, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.0029969628817093107}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_recall": 0.05806614564935589, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.0027269030308790685}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_fmeasure": 0.04266745301669875, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.002122467346772042}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_precision": 0.008207881019302006, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.0010086514951802858}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_recall": 0.008521702795534656, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0010434649664570375}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_fmeasure": 0.006554418985992436, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.0007815781854311512}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_precision": 0.04597127256330522, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.0025493206390164915}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_recall": 0.051020708361635456, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.0024526062149060925}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_fmeasure": 0.036366524875545106, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0018289351480190433}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_precision": 0.04719764857087024, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0026618730300778984}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_recall": 0.050823488012879496, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.0024311881894851393}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_fmeasure": 0.03690636788662361, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018560807675874356}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_3.json new file mode 100644 index 0000000000000000000000000000000000000000..2569e0b04398f45be2bfe4d2d7018136ba57b19b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "no prompt needed", "bleu": 0.22144147011965754, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.05131138433756984}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_precision": 0.058386033932004415, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.0030880102581303886}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_recall": 0.05486532333879447, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.002608469514368819}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_fmeasure": 0.04452655769234325, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.0021712328467205486}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_precision": 0.008602699160749428, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.0009813451014566705}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_recall": 0.007308424504803039, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0008927033877862982}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_fmeasure": 0.006348389170194352, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.0007281347015003358}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_precision": 0.05007522678633194, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.0026478813192163213}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_recall": 0.048399277860299794, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.0023392317754922483}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_fmeasure": 0.038296677712480076, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0018715868727211123}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_precision": 0.05143163493997383, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0027770376467427965}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_recall": 0.04819611262496829, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.0023229320235610062}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_fmeasure": 0.038779230929206605, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.001893632110275806}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_4.json new file mode 100644 index 0000000000000000000000000000000000000000..7da72fe95cb56e686086154564ea6ba85ab676d4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "no prompt needed", "bleu": 0.18473186157561908, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.04072950696800683}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_precision": 0.06712446822614468, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.0033160597701479893}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_recall": 0.06019191056988439, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.002736892229053133}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_fmeasure": 0.05159212402267852, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.0023638676475464648}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_precision": 0.00964919360937356, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.0010051600074264555}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_recall": 0.008577476981962201, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0009456245783267479}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_fmeasure": 0.0074306129720465705, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.0007606984807758116}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_precision": 0.05818637904982665, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.0029044534046547958}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_recall": 0.05347769921709429, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.0024762222522701598}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_fmeasure": 0.045035878449402864, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.002091652415092048}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_precision": 0.059446564318682005, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0029928762915145727}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_recall": 0.0537919766565263, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.0024838459656666596}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_fmeasure": 0.04570769475572357, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.0021186626160801304}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e9065bf14d86e1de154141f92f72e03e9a5fc170 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_no-prompt-needed_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "no prompt needed", "bleu": 0.3674534532595343, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "bleu_stderr": 0.044535440751908385}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_precision": 0.06632940430625783, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_precision_stderr": 0.003221290438735765}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_recall": 0.06301059430183462, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_recall_stderr": 0.0028293221861692515}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge1_fmeasure": 0.05237001461800124, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge1_fmeasure_stderr": 0.002390063573522162}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_precision": 0.010990734326689173, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_precision_stderr": 0.0011480661925135293}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_recall": 0.010346369422141026, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_recall_stderr": 0.0010512298188535155}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rouge2_fmeasure": 0.008657019208894664, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rouge2_fmeasure_stderr": 0.0008613172115835112}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_precision": 0.05733867044052891, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_precision_stderr": 0.002753785198676713}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_recall": 0.056005566309979465, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_recall_stderr": 0.0025635471231317537}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeL_fmeasure": 0.045594480368473495, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeL_fmeasure_stderr": 0.0020873498805373575}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_precision": 0.05908856304665778, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_precision_stderr": 0.0029043642978511183}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_recall": 0.05634193274869875, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_recall_stderr": 0.0025654170882293886}, {"task_name": "piqa", "prompt_name": "no prompt needed", "rougeLsum_fmeasure": 0.046277441891386925, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "c8c45ef1-2ffc-43d7-8710-b98c2fc4f699", "prompt_jinja": "{{goal}}\n|||\n{{[sol1[0].lower() + sol1[1:], sol2[0].lower() + sol2[1:]][label]}}", "prompt_original_task": false, "comment": "", "rougeLsum_fmeasure_stderr": 0.0021092213962826474}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d8253ea57f545f9541230d4ab95cb53431964f9b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc": 0.49510337323177367, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01166526473007815}, {"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc_norm": 0.49510337323177367, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01166526473007815}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d5e5071bca192483e89bcc6f360689dcf4d6bc3d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc": 0.5038084874863983, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0116654857447468}, {"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc_norm": 0.5038084874863983, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.0116654857447468}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_2.json new file mode 100644 index 0000000000000000000000000000000000000000..7c280e2d63e371d6e9efa69ad0f89408811da189 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc": 0.4956474428726877, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011665382144642383}, {"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc_norm": 0.4956474428726877, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011665382144642383}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7232202bb314adb8cfe5a6a684f90e3cce314fec --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc": 0.5250272034820457, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011651200967623707}, {"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc_norm": 0.5250272034820457, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011651200967623707}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_4.json new file mode 100644 index 0000000000000000000000000000000000000000..078605b1099c93d08aeb23317d1c1d2865fa87d5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc": 0.5239390642002176, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01165244562107926}, {"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc_norm": 0.5239390642002176, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01165244562107926}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b662080570ac89f1a64f810343ee0b402edb0d92 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_pick_correct_choice_index_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc": 0.5076169749727966, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011664470424044976}, {"task_name": "piqa", "prompt_name": "pick_correct_choice_index", "acc_norm": 0.5076169749727966, "fixed_answer_choice_list": ["1", "2"], "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "44778818-7b73-4262-a294-c00fc32b6c2c", "prompt_jinja": "Sentence: {{goal}}\n\nChoice {{answer_choices[0]}}: {{sol1}}\n\nChoice {{answer_choices[1]}}: {{sol2}}\n\nWhat is the index of the correct choice for ending for the sentence?\n\nAnswer:\n\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011664470424044976}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d2f1cf818f30410652060627e3a08ca25eb5c400 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc": 0.5233949945593036, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01165304715592779}, {"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc_norm": 0.5250272034820457, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011651200967623706}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..a3e663267c417c9543656fc3dd492b6fa48878c3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc": 0.5212187159956474, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011655314732288858}, {"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc_norm": 0.5223068552774756, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011654208652596474}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6ae4be9848b70c308d2e7db7e368cd4290e6f09f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc": 0.5255712731229597, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011650557844573578}, {"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc_norm": 0.5163220892274211, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011659606710151779}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..bcfe703ceea7a78417b296967ed7932aebe2e998 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc": 0.5206746463547334, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011655846995729703}, {"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc_norm": 0.5163220892274211, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011659606710151779}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..a5209307ef0bdc5c584f2d096ed6548a158eec07 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc": 0.5195865070729053, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01165686997928846}, {"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc_norm": 0.514145810663765, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011661154475524835}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c1c66faab502ac2819cf0f44ad284d0cd358e66e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc": 0.5125136017410229, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011662170084916892}, {"task_name": "piqa", "prompt_name": "what_is_the_correct_ending", "acc_norm": 0.5081610446137106, "fixed_answer_choice_list": null, "dataset_path": "piqa", "dataset_name": null, "subset": null, "prompt_id": "16e97a16-c958-4956-bfba-279f88dafd5b", "prompt_jinja": "Goal: {{goal}}\n\nWhich is the correct ending?\n- {{sol1}}\n- {{sol2}}\n\nAnswer:\n|||\n{{answer_choices[label]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011664270112244223}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.json new file mode 100644 index 0000000000000000000000000000000000000000..14fe6abbb414ca8424626d174a98b8e4c075cfdf --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc": 0.365, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015231776226264914}, {"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc_norm": 0.36, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015186527932040122}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.json new file mode 100644 index 0000000000000000000000000000000000000000..73f03ced9410b57b29b646e556eb064473c311ab --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc": 0.393, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015452824654081496}, {"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc_norm": 0.388, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015417317979911076}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.json new file mode 100644 index 0000000000000000000000000000000000000000..5a153546caad4162da88898388611c00465c08f4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc": 0.386, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015402637476784385}, {"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc_norm": 0.387, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015410011955493932}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.json new file mode 100644 index 0000000000000000000000000000000000000000..819340fe45b280d0cc7f9fd6bc01651a77c6465f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc": 0.383, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01538010232565271}, {"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc_norm": 0.379, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01534909100222535}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e9ea9d2779a8b450c94d9df0af932887c6152214 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc": 0.393, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015452824654081496}, {"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc_norm": 0.388, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015417317979911076}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.json new file mode 100644 index 0000000000000000000000000000000000000000..bc19fbbbd5bd1eea585030b14a566b6871cd38a6 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc": 0.384, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015387682761897068}, {"task_name": "sciq", "prompt_name": "Direct Question (Closed Book)", "acc_norm": 0.388, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "0af52ad2-2b12-4700-b664-cd26d2da6dc1", "prompt_jinja": "Q: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015417317979911077}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_0.json new file mode 100644 index 0000000000000000000000000000000000000000..aa4a0e977fe7333b1c1ef8c728450226f2b1e3cd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question", "acc": 0.663, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014955087918653595}, {"task_name": "sciq", "prompt_name": "Direct Question", "acc_norm": 0.567, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01567663091218133}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_1.json new file mode 100644 index 0000000000000000000000000000000000000000..4d36f7f4cb101cdbb57d3aefb4a675e35a3c8f27 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question", "acc": 0.715, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014282120955200485}, {"task_name": "sciq", "prompt_name": "Direct Question", "acc_norm": 0.648, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015110404505648661}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a457ee5c24a77bc3c180f2d2dece5cb08e7ac43c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question", "acc": 0.71, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01435639599990569}, {"task_name": "sciq", "prompt_name": "Direct Question", "acc_norm": 0.664, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014944140233795023}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_3.json new file mode 100644 index 0000000000000000000000000000000000000000..981687ed69e6cbd99c879c60f621537c95faf778 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question", "acc": 0.722, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014174516461485265}, {"task_name": "sciq", "prompt_name": "Direct Question", "acc_norm": 0.682, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014734079309311901}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1f7964bf29fba68b8871ba1b95f174f6e28345 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question", "acc": 0.724, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014142984975740668}, {"task_name": "sciq", "prompt_name": "Direct Question", "acc_norm": 0.7, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01449862787336143}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_5.json new file mode 100644 index 0000000000000000000000000000000000000000..ba963c162f2a7176ba6d5405daa6d98de5842d27 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Direct-Question_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Direct Question", "acc": 0.728, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014078856992462621}, {"task_name": "sciq", "prompt_name": "Direct Question", "acc_norm": 0.695, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "d417fcfb-9f00-4186-95d8-e63609495164", "prompt_jinja": "Answer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014566646394664382}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b16b25f1f3767c4699f6ee26f4ecd5245bfbab7f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc": 0.372, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.015292149942040577}, {"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc_norm": 0.347, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.015060472031706618}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cf286a18beedc9099df2b56192be91a06f3ce24e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc": 0.32, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014758652303574874}, {"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc_norm": 0.329, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014865395385928362}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2da3bc0c860cc8f0b0a585689eec5f92b3b1fb65 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc": 0.276, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014142984975740668}, {"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc_norm": 0.291, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014370995982377946}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.json new file mode 100644 index 0000000000000000000000000000000000000000..27a79cd445e4df5ebbb313d67372b2fe229a2a07 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc": 0.3, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014498627873361425}, {"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc_norm": 0.308, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.01460648312734276}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.json new file mode 100644 index 0000000000000000000000000000000000000000..95e2626974279f9998f753816b27a3b60015ac95 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc": 0.306, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014580006055436965}, {"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc_norm": 0.331, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.01488827258820393}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.json new file mode 100644 index 0000000000000000000000000000000000000000..bfa7a1d6b08938ea91a83fc410d220020d931402 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc": 0.298, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014470846741134722}, {"task_name": "sciq", "prompt_name": "Multiple Choice (Closed Book)", "acc_norm": 0.308, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "15b0a989-84e4-4f1c-8ac1-12dbfa2ff42a", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014606483127342763}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2ce1692b4bd7d2e426a20a69f62cb36c95e4d498 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc": 0.516, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015811198373114878}, {"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc_norm": 0.434, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015680876566375058}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.json new file mode 100644 index 0000000000000000000000000000000000000000..3bb9282317202816201494ebc74f2140c9e65d85 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc": 0.395, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015466551464829342}, {"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc_norm": 0.406, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015537226438634602}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.json new file mode 100644 index 0000000000000000000000000000000000000000..90c5e1601789b2c4109cee3dbb48451c88d8dc6f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc": 0.323, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014794927843348632}, {"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc_norm": 0.324, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014806864733738859}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a890196edec999cbda620f15bcdc4b7b175d7b6e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc": 0.319, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014746404865473494}, {"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc_norm": 0.329, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014865395385928357}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.json new file mode 100644 index 0000000000000000000000000000000000000000..254252e9fd5d79a03957616fdfd15aea04c2eeda --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc": 0.322, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014782913600996664}, {"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc_norm": 0.327, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014842213153411247}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.json new file mode 100644 index 0000000000000000000000000000000000000000..cd89079a37e5d6c39b96c29c973cd4c73c3be0e3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc": 0.313, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014671272822977881}, {"task_name": "sciq", "prompt_name": "Multiple Choice Question First", "acc_norm": 0.309, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "368e29fb-506d-4a4e-ac33-0af8d6e1729b", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nQ: {{question}}\n\n\nRead this paragraph and choose the correct option from the provided answers:\n\n{{support}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\n\nA:|||{{answer_choices[3]}}\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014619600977206482}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a7abce949d4bdb351329d602adb024bbb4cfb99d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice", "acc": 0.482, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.015809045699406728}, {"task_name": "sciq", "prompt_name": "Multiple Choice", "acc_norm": 0.438, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01569721001969469}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_1.json new file mode 100644 index 0000000000000000000000000000000000000000..1dc9e039a9084cac9d8e1547551af07c2ef436af --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice", "acc": 0.335, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014933117490932573}, {"task_name": "sciq", "prompt_name": "Multiple Choice", "acc_norm": 0.355, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.015139491543780532}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_2.json new file mode 100644 index 0000000000000000000000000000000000000000..839a8b52ba3b73a3e132e3db92c6624e5d280835 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice", "acc": 0.28, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014205696104091512}, {"task_name": "sciq", "prompt_name": "Multiple Choice", "acc_norm": 0.282, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014236526215291343}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8bae949a01a780964e5e9c49f8b0c78bddc218dc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice", "acc": 0.28, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014205696104091512}, {"task_name": "sciq", "prompt_name": "Multiple Choice", "acc_norm": 0.293, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014399942998441275}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_4.json new file mode 100644 index 0000000000000000000000000000000000000000..823e9e5ecede4d8ffbe9d757a090626b95460f34 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice", "acc": 0.308, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014606483127342761}, {"task_name": "sciq", "prompt_name": "Multiple Choice", "acc_norm": 0.322, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014782913600996662}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c96f2836da86d35ee0d2a51b4d8ad250ffc80198 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_sciq_Multiple-Choice_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "sciq", "prompt_name": "Multiple Choice", "acc": 0.289, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014341711358296177}, {"task_name": "sciq", "prompt_name": "Multiple Choice", "acc_norm": 0.292, "fixed_answer_choice_list": null, "dataset_path": "sciq", "dataset_name": null, "subset": null, "prompt_id": "63c22e8a-7029-4ce3-bd26-6ca6a1541563", "prompt_jinja": "{% set order = [[0, 1, 2, 3], [0, 1, 3, 2], [0, 2, 1, 3], [0, 2, 3, 1], [0, 3, 1, 2], [0, 3, 2, 1],\n [1, 0, 2, 3], [1, 0, 3, 2], [1, 2, 0, 3], [1, 2, 3, 0], [1, 3, 0, 2], [1, 3, 2, 0],\n [2, 1, 0, 3], [2, 1, 0, 2], [2, 0, 1, 3], [2, 0, 3, 1], [2, 3, 1, 0], [2, 3, 0, 1],\n [3, 1, 2, 0], [3, 1, 0, 2], [3, 2, 1, 0], [3, 2, 0, 1], [3, 0, 1, 2], [3, 0, 2, 1]] | choice %}\nAnswer the following question given this paragraph: \n\n{{support}}\n\n\nQ: {{question}}\n\n Choices:\n\n- {{ answer_choices[order[0]] }}\n\n- {{ answer_choices[order[1]] }}\n\n- {{ answer_choices[order[2]] }}\n\n- {{ answer_choices[order[3]] }}\n\nA:|||{{answer_choices[3]}}\n\n", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01438551156347735}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..ee761a4fad08b715775cb14a127abc43d0c761cd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc": 0.48583645109567075, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011557792331301673}, {"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc_norm": 0.48850881881346875, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011559378273599123}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..477c286452161f2bf9b8808ab0a584614a64a038 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc": 0.47835382148583644, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011551591851683333}, {"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc_norm": 0.4890432923570283, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011559655791130734}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..8035b667f0afab62ec9e534d9e33328e05d073ae --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc": 0.4767504008551577, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01154992548392746}, {"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc_norm": 0.47728487439871725, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011550494192008943}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..09598c7bdd3305e0f0bc583966b9fd4874e2e919 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc": 0.4681988241582042, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01153902203511123}, {"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc_norm": 0.4836985569214324, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011556285484521566}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..10b12a4193957002eb5ed6a399ffac2a6ff97dbc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc": 0.467129877071085, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011537420054210303}, {"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc_norm": 0.4756814537680385, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01154874830148732}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..554ac09cb5235c43ed198cc5a79d22cce98290b8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc": 0.46392303580972744, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01153229486915312}, {"task_name": "story_cloze_2016", "prompt_name": "Answer Given options", "acc_norm": 0.47247461250668094, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a4946f9-a0e2-4fbb-aee8-b26ead2cf6b8", "prompt_jinja": "{{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What is a possible continuation for the story given the following options ? - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011544898473864583}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e6ac8e3eb9100f3b0694744d0bee756bbc970b4f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc": 0.5066809192944949, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011561400034509398}, {"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc_norm": 0.5259219668626403, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011546883081384901}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..01bcfb92bcae6a7fd95fc29bac7582b17cc8a534 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc": 0.47835382148583644, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011551591851683333}, {"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc_norm": 0.49438802779262425, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011561703928784335}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2b0a19de2b0983d5090e627124806b7e013a6249 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc": 0.4794227685729556, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011552636515221862}, {"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc_norm": 0.4906467129877071, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011560409019420362}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7f7c3345412b07225e75e38b6bb9309a122ae6da --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc": 0.4751469802244789, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01154813982307477}, {"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc_norm": 0.4735435595938001, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011546234813777404}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3704775de752700d62b5a5b35fece8cfa7fe3a39 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc": 0.467129877071085, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011537420054210303}, {"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc_norm": 0.4692677712453234, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011540570846495542}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..9b1b339db8468a2d7298d31400cdff514890b5b4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc": 0.45911277391769106, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01152370806018208}, {"task_name": "story_cloze_2016", "prompt_name": "Choose Story Ending", "acc_norm": 0.46873329770176375, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "1a9d53bc-eb77-4e7c-af6e-3d15b79d6cf1", "prompt_jinja": "Read the following story :\n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose a possible ending for the previous story from the following options: \n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011539803085637734}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..7acf416b1dc6d6db37541d8424edde0f6e833c5e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.json @@ -0,0 +1 @@ +{"results": [], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..460c877067176f51d810be5fbaf9b31ea0641b43 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.json @@ -0,0 +1 @@ +{"results": [], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e6ad0b513b216bc135d21f8ca60dce879f917af4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.json @@ -0,0 +1 @@ +{"results": [], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..c897dfaaf01868dd9b699ee8bc211e776f55b680 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.json @@ -0,0 +1 @@ +{"results": [], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..60bf96c3ed8cfcebc5c0ab51c3a0213d6675ed80 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.json @@ -0,0 +1 @@ +{"results": [], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..77347e8b2d92ca0edea5e17a77786f6d9c90119e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.json @@ -0,0 +1 @@ +{"results": [], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c9b77af9e9db549f7b1739eeb67a1e6c773e8081 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc": 0.47728487439871725, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011550494192008947}, {"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc_norm": 0.48476750400855156, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011557065368348286}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..452da90c1296f3c5a6f64d8dc7c19eb82f70b1a3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc": 0.47247461250668094, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011544898473864581}, {"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc_norm": 0.48476750400855156, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011557065368348288}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..85ae637c136960e0219a9686a95d009ab8ffa4d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc": 0.4719401389631213, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011544210396951667}, {"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc_norm": 0.47728487439871725, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011550494192008943}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..4964388fa7157dae42927108b9f41661d42dea98 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc": 0.4692677712453234, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011540570846495544}, {"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc_norm": 0.47728487439871725, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011550494192008941}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..37964fbc50c4f3a0c13e1648385cf7ce3635f405 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc": 0.4660609299839658, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011535764881641411}, {"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc_norm": 0.4708711918760021, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011542794417345717}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..0456df2a3af9b3a6015946212685e13acbbb4011 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc": 0.4580438268305719, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011521653168224729}, {"task_name": "story_cloze_2016", "prompt_name": "Novel Correct Ending", "acc_norm": 0.4649919828968466, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "c6f3d802-4f97-449f-a911-03470d418f7d", "prompt_jinja": "I read the following novel: {{input_sentence_1}} {{input_sentence_2}} {{input_sentence_3}} {{input_sentence_4}} What do you think is the most probable ending? You can choose from the following options: - {{answer_choices | join(\"\\n- \")}} ||| {{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011534056494505859}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..3e5b0c4e404163d892d484cec2ccf15b3ddce702 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc": 0.49812934259754144, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011562351329083266}, {"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc_norm": 0.5189738107963656, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.0115541041740197}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..e2cc93afa4f9fa1c1910697f5df9e9a99204e61e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc": 0.4794227685729556, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011552636515221862}, {"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc_norm": 0.48850881881346875, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011559378273599118}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..81c639251ae88d828f9fcb69756ddea36f7945e5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc": 0.4740780331373597, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011546883081384903}, {"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc_norm": 0.4831640833778728, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011555875693960773}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..4e8d7a9465a9fb626efe1f6ab2a9cd23b7b8c911 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc": 0.467129877071085, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0115374200542103}, {"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc_norm": 0.4767504008551577, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011549925483927456}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c7d04b667ebcfd2ff6fae036f52f0832b91ec37e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc": 0.46392303580972744, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01153229486915312}, {"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc_norm": 0.47033671833244256, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011542066509767012}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..bceb4bfd1ff2edfa6e33eb77a83e768db99a0f82 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc": 0.4537680384820951, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.011512899199863038}, {"task_name": "story_cloze_2016", "prompt_name": "Story Continuation and Options", "acc_norm": 0.4633885622661678, "fixed_answer_choice_list": null, "dataset_path": "story_cloze", "dataset_name": "2016", "subset": null, "prompt_id": "b5c8445f-2d3a-4691-bdd5-58956816702f", "prompt_jinja": "What is a possible continuation for the following story ? \n\n{{input_sentence_1}}\n{{input_sentence_2}}\n{{input_sentence_3}}\n{{input_sentence_4}}\n\nChoose from the following options:\n- {{answer_choices | join(\"\\n- \")}}\n|||\n\n{{answer_choices[answer_right_ending -1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.011531394084549623}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..8f50e262044201cf2689cff9e74a1c25a7a1772f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc": 0.5342960288808665, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.03002557981936642}, {"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc_norm": 0.4729241877256318, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030052303463143706}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..e333ae59e784f8ba36ff319fe6eec5a878fa6147 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc": 0.4981949458483754, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030096267148976633}, {"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc_norm": 0.5018050541516246, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030096267148976626}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..494a6df3f5ae03702a5e88426e99d9efe1c0bc74 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc": 0.5234657039711191, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030063300411902652}, {"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc_norm": 0.5234657039711191, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030063300411902652}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..b2236da6e5667f46ec8b8da6a291706b360ec3ee --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc": 0.516245487364621, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030080573208738064}, {"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc_norm": 0.49097472924187724, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030091559826331334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e9401e3605aa183230def9caa4feaa9ca618485f --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc": 0.5054151624548736, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030094698123239966}, {"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc_norm": 0.5090252707581228, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030091559826331334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..8c26da5df244225f5733c9793ec288fcafda4a61 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_GPT-3-style_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc": 0.5018050541516246, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030096267148976633}, {"task_name": "superglue_rte", "prompt_name": "GPT-3 style", "acc_norm": 0.5054151624548736, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "8fb1c6aa-20e9-438c-bece-c6af1c746449", "prompt_jinja": "{{premise}}\nQuestion: {{hypothesis}} True or False? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030094698123239966}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c2c551618f2b682213bc0deffdecfebe80ffb057 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030052303463143706}, {"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc_norm": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030052303463143706}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..bba241c7951e4a28deaf0057fdbaa4b099d3a854 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc": 0.5306859205776173, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030039730592197812}, {"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc_norm": 0.5415162454873647, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.029992535385373314}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6af94d8a82603c1d82fd30b1dc3f7bc12a387a0b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc": 0.5090252707581228, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030091559826331334}, {"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc_norm": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030080573208738064}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7fef3c80ab67f95dbf6a235a4a9c080beabadcd4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc": 0.5234657039711191, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.03006330041190266}, {"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc_norm": 0.51985559566787, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030072723167317177}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..06f0d7d8900b7bd538216a3bc48ca14494f31ddd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030080573208738064}, {"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc_norm": 0.5306859205776173, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030039730592197816}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..407a77fe8a5465557e2942638d17c9749d91cfb4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030080573208738064}, {"task_name": "superglue_rte", "prompt_name": "MNLI crowdsource", "acc_norm": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2b52a83c-0021-41fe-b44c-5aaa076d71a2", "prompt_jinja": "{{premise}} Using only the above description and what you know about the world, is \"{{hypothesis}}\" definitely correct? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030086851767188564}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.json new file mode 100644 index 0000000000000000000000000000000000000000..f227a008103158ec4051dde2d9462e818f040ab9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc": 0.5054151624548736, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030094698123239966}, {"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc_norm": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030052303463143706}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.json new file mode 100644 index 0000000000000000000000000000000000000000..22719570a0e60b6d6ffc80d10c2c636316fc05c5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc": 0.49458483754512633, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030094698123239966}, {"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc_norm": 0.5090252707581228, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030091559826331334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1e09c53b7843fe80da56afcb8de7a0f1f27e815d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc": 0.5054151624548736, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030094698123239966}, {"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc_norm": 0.5054151624548736, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030094698123239966}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.json new file mode 100644 index 0000000000000000000000000000000000000000..97296f2e9eb6d0e1be80d14436dce8c0fa2e08fc --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030086851767188564}, {"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc_norm": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030080573208738064}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.json new file mode 100644 index 0000000000000000000000000000000000000000..6db7045c44c057f33c50d4c40a45132851f278c4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc": 0.5018050541516246, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030096267148976626}, {"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc_norm": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030086851767188564}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.json new file mode 100644 index 0000000000000000000000000000000000000000..58e679d5c59b5d3260c0bba395891bcbcaeed0b2 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc": 0.4981949458483754, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030096267148976633}, {"task_name": "superglue_rte", "prompt_name": "does it follow that", "acc_norm": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "e2fb58f2-b1f2-4aef-b74b-c4ee1c571fff", "prompt_jinja": "Given that {{premise}} Does it follow that {{hypothesis}} Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030080573208738064}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2ffcd51e033f76ff1d646817ae387b96deddcf7d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030052303463143706}, {"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc_norm": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030052303463143706}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_1.json new file mode 100644 index 0000000000000000000000000000000000000000..706ced7d58d8c6919216158e0526ab694e5a7ce1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc": 0.48375451263537905, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030080573208738064}, {"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc_norm": 0.47653429602888087, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.03006330041190266}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2b38c8fd4b5d774905840991afa000dd29c587ac --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc": 0.5018050541516246, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030096267148976633}, {"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc_norm": 0.5090252707581228, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030091559826331334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_3.json new file mode 100644 index 0000000000000000000000000000000000000000..96da52eff94bf93668be1c12b3c820896d719644 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030080573208738064}, {"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc_norm": 0.5234657039711191, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.03006330041190266}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_4.json new file mode 100644 index 0000000000000000000000000000000000000000..549519ef3487a4eb36ad4fb2410446a3aa90972c --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030086851767188564}, {"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc_norm": 0.516245487364621, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030080573208738064}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a1cdadd49d4a7a82c563ea6f0d4873e4d18d3ce7 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_guaranteed-true_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030086851767188564}, {"task_name": "superglue_rte", "prompt_name": "guaranteed true", "acc_norm": 0.51985559566787, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "2d0d63da-ffcf-4f6e-941a-b8da922be43e", "prompt_jinja": "Given {{premise}} Is it guaranteed true that \"{{hypothesis}}\"? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030072723167317177}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c84cde16cb3e6b81a1eafe6269de3fb271d72c76 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "should assume", "acc": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030052303463143706}, {"task_name": "superglue_rte", "prompt_name": "should assume", "acc_norm": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030052303463143706}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_1.json new file mode 100644 index 0000000000000000000000000000000000000000..268fa3b7b2c99a86d7248d3cdecaf0623aff7ff5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "should assume", "acc": 0.4981949458483754, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030096267148976633}, {"task_name": "superglue_rte", "prompt_name": "should assume", "acc_norm": 0.5234657039711191, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.03006330041190266}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0aa0117e0da232667c71f804f8753ca2c4cc462e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "should assume", "acc": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030086851767188564}, {"task_name": "superglue_rte", "prompt_name": "should assume", "acc_norm": 0.5090252707581228, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030091559826331334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_3.json new file mode 100644 index 0000000000000000000000000000000000000000..b205d12c3d6c2482f3a160e167479e24a5004836 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "should assume", "acc": 0.5270758122743683, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030052303463143706}, {"task_name": "superglue_rte", "prompt_name": "should assume", "acc_norm": 0.5234657039711191, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.03006330041190266}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_4.json new file mode 100644 index 0000000000000000000000000000000000000000..2facb46110e18a741d5bf5d9b59b440886933285 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "should assume", "acc": 0.5342960288808665, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030025579819366426}, {"task_name": "superglue_rte", "prompt_name": "should assume", "acc_norm": 0.5342960288808665, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030025579819366426}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a12305332b2779fa2fa1b0c9d402c103d5a0a1cf --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_superglue_rte_should-assume_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "superglue_rte", "prompt_name": "should assume", "acc": 0.5126353790613718, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.030086851767188564}, {"task_name": "superglue_rte", "prompt_name": "should assume", "acc_norm": 0.5054151624548736, "fixed_answer_choice_list": ["Yes", "No"], "dataset_path": "super_glue", "dataset_name": "rte", "subset": null, "prompt_id": "b8dc85c6-28b6-4340-979a-8e77c2a0dde8", "prompt_jinja": "Given {{premise}} Should we assume that \"{{hypothesis}}\" is true? Yes or no? ||| {% if label != -1 %}{{ answer_choices[label] }}{% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.030094698123239966}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_0.json new file mode 100644 index 0000000000000000000000000000000000000000..87005c11d87d189916d630294a481757230fe3ce --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "Replace", "acc": 0.4996053670086819, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052481306049512}, {"task_name": "winogrande", "prompt_name": "Replace", "acc_norm": 0.49329123914759276, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014051220692330346}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_1.json new file mode 100644 index 0000000000000000000000000000000000000000..2a8597d4ddf5cd7b2280c6990179261f06403d3b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "Replace", "acc": 0.5035516969218626, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052131146915864}, {"task_name": "winogrande", "prompt_name": "Replace", "acc_norm": 0.5019731649565904, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014052376259225632}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f43374b89a9da7d14961d194d617e53bcf1e8a74 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "Replace", "acc": 0.4996053670086819, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052481306049516}, {"task_name": "winogrande", "prompt_name": "Replace", "acc_norm": 0.4940805051302289, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01405150083848581}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_3.json new file mode 100644 index 0000000000000000000000000000000000000000..64645e860b613cb543dede938e21276dcc6c5bd3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "Replace", "acc": 0.4956590370955012, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051956064076892}, {"task_name": "winogrande", "prompt_name": "Replace", "acc_norm": 0.5027624309392266, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014052271211616436}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ffe59b8e3465786a0e5bb5c13b8964f15000b403 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "Replace", "acc": 0.4925019731649566, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014050905521228573}, {"task_name": "winogrande", "prompt_name": "Replace", "acc_norm": 0.500394632991318, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01405248130604952}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_5.json new file mode 100644 index 0000000000000000000000000000000000000000..7567e38e3d06fedaf9fea506c59c94e02fc29216 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_Replace_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "Replace", "acc": 0.4980268350434096, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052376259225636}, {"task_name": "winogrande", "prompt_name": "Replace", "acc_norm": 0.49171270718232046, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "e7e42e9e-bc57-46ed-ad8a-76a5b90a5bb9", "prompt_jinja": "{{sentence}}\nReplace the _ in the above sentence with the correct option: \n- {{option1}}\n- {{option2}}\n|||\n{% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014050555322824194}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_0.json new file mode 100644 index 0000000000000000000000000000000000000000..7400ebfb33facbb2fab88d160f263aae19a628d1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "True or False", "acc": 0.494869771112865, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014051745961790516}, {"task_name": "winogrande", "prompt_name": "True or False", "acc_norm": 0.47908445146014206, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014040185494212952}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_1.json new file mode 100644 index 0000000000000000000000000000000000000000..ac4faa2dcfcbe711a4196161593aec1ec634c2f3 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "True or False", "acc": 0.5011838989739542, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014052446290529012}, {"task_name": "winogrande", "prompt_name": "True or False", "acc_norm": 0.505130228887135, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014051745961790513}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_2.json new file mode 100644 index 0000000000000000000000000000000000000000..ca62bd6f54dde0330691b72eadfdc7fe02bd6c07 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "True or False", "acc": 0.5098658247829518, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014049749833367596}, {"task_name": "winogrande", "prompt_name": "True or False", "acc_norm": 0.500394632991318, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014052481306049516}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_3.json new file mode 100644 index 0000000000000000000000000000000000000000..e8158a0eae5ab6d8b921e52ae17d13d2f1baed00 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "True or False", "acc": 0.5059194948697711, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014051500838485807}, {"task_name": "winogrande", "prompt_name": "True or False", "acc_norm": 0.5114443567482242, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014048804199859325}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e203e17d3848b0597c1916e826f7b3c92daca676 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "True or False", "acc": 0.5201262825572218, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.01404109666434433}, {"task_name": "winogrande", "prompt_name": "True or False", "acc_norm": 0.5288082083662194, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014029141615909617}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d67a8e618efed01d26c72ae2a1781875c36f8fa8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_True-or-False_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "True or False", "acc": 0.5185477505919495, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_stderr": 0.014042813708888378}, {"task_name": "winogrande", "prompt_name": "True or False", "acc_norm": 0.5138121546961326, "fixed_answer_choice_list": ["True", "False"], "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "d11378d1-2f24-4509-bbbc-bfa2921300d5", "prompt_jinja": "The _ in the sentence below refers to {{option1}}. True or False?\n{{sentence}}|||\n{{answer_choices[answer|int - 1]}}", "prompt_original_task": false, "comment": "", "acc_norm_stderr": 0.014047122916440415}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e40a8c72d3129a5b7359e3895b6741aa5ce8612b --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc": 0.494869771112865, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051745961790516}, {"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc_norm": 0.4988161010260458, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014052446290529024}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cde2ece4355cd4bfdf6e623e538ed50349271000 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc": 0.5209155485398579, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014040185494212947}, {"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc_norm": 0.505130228887135, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014051745961790513}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.json new file mode 100644 index 0000000000000000000000000000000000000000..85e76c80c180ee9cfef8263bd4fbb8eb667d0326 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc": 0.49329123914759276, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051220692330349}, {"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc_norm": 0.5074980268350434, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01405090552122858}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.json new file mode 100644 index 0000000000000000000000000000000000000000..313366ac8e8651a27fbc432cca468db97ae04644 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc": 0.489344909234412, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0140492945362904}, {"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc_norm": 0.5074980268350434, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01405090552122858}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bd72c5644893e26f22ff9e6dce235601f5db7222 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc": 0.48303078137332284, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014044390401612976}, {"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc_norm": 0.5082872928176796, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014050555322824189}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e6c2b21e1df97e61edf2627e9661d6158c500dfd --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc": 0.5043409629044988, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051956064076892}, {"task_name": "winogrande", "prompt_name": "does underscore refer to", "acc_norm": 0.5090765588003157, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "0f23f058-5b4d-42a3-92d4-5d60688aa90c", "prompt_jinja": "{{ sentence }} In the previous sentence, does _ refer to {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014050170094497704}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_0.json new file mode 100644 index 0000000000000000000000000000000000000000..09ea011ee80598feed8ed8a9474f6c1691945c70 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "stand for", "acc": 0.4940805051302289, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051500838485807}, {"task_name": "winogrande", "prompt_name": "stand for", "acc_norm": 0.48697711128650356, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014047718393997667}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d8340a35f9d8cbaf6262870b55840c2fa60e6e1a --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "stand for", "acc": 0.5059194948697711, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051500838485807}, {"task_name": "winogrande", "prompt_name": "stand for", "acc_norm": 0.4988161010260458, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014052446290529024}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_2.json new file mode 100644 index 0000000000000000000000000000000000000000..7859793731146268c975c26c95622ce267f895f4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "stand for", "acc": 0.5035516969218626, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052131146915853}, {"task_name": "winogrande", "prompt_name": "stand for", "acc_norm": 0.494869771112865, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01405174596179052}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_3.json new file mode 100644 index 0000000000000000000000000000000000000000..2690e0115f94391c0b8ecb3b7cbc96fa891e0ab1 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "stand for", "acc": 0.5114443567482242, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014048804199859325}, {"task_name": "winogrande", "prompt_name": "stand for", "acc_norm": 0.5019731649565904, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014052376259225636}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_4.json new file mode 100644 index 0000000000000000000000000000000000000000..811cf54d96fbf450db71b7723938f0f48c1730f4 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "stand for", "acc": 0.5059194948697711, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051500838485807}, {"task_name": "winogrande", "prompt_name": "stand for", "acc_norm": 0.494869771112865, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014051745961790523}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_5.json new file mode 100644 index 0000000000000000000000000000000000000000..45e474348dd3c0126d530440569bf8d8c9310ba9 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_stand-for_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "stand for", "acc": 0.5043409629044988, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.0140519560640769}, {"task_name": "winogrande", "prompt_name": "stand for", "acc_norm": 0.5074980268350434, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5080f912-fac8-400f-983c-944baf9b10c0", "prompt_jinja": "In the sentence below, does the _ stand for {{answer_choices[0]}} or {{answer_choices[1]}}?\n{{sentence}}|||\n{{answer_choices[answer | int - 1]}}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014050905521228573}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_0.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_0.json new file mode 100644 index 0000000000000000000000000000000000000000..00e0605e03bc22787c068b2de7979cfa8a1ba44d --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_0.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "underscore refer to", "acc": 0.4940805051302289, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014051500838485807}, {"task_name": "winogrande", "prompt_name": "underscore refer to", "acc_norm": 0.4980268350434096, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014052376259225636}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 0, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_1.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_1.json new file mode 100644 index 0000000000000000000000000000000000000000..6794060ab0a2d8b14f92586e8925b09b110c6ab5 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_1.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "underscore refer to", "acc": 0.4988161010260458, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052446290529015}, {"task_name": "winogrande", "prompt_name": "underscore refer to", "acc_norm": 0.5059194948697711, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01405150083848581}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_2.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_2.json new file mode 100644 index 0000000000000000000000000000000000000000..02e1cd20ddcbda8a77b8bf12233f99b140361528 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_2.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "underscore refer to", "acc": 0.5130228887134964, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.01404771839399767}, {"task_name": "winogrande", "prompt_name": "underscore refer to", "acc_norm": 0.5153906866614049, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014045826789783658}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_3.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9008307770e23114ccc7929d5c580400f6a9546e --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_3.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "underscore refer to", "acc": 0.5035516969218626, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014052131146915867}, {"task_name": "winogrande", "prompt_name": "underscore refer to", "acc_norm": 0.5043409629044988, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014051956064076906}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_4.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8adf5542d1b50347fa8c6935d5c36ec3da6c9df8 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_4.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "underscore refer to", "acc": 0.516179952644041, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014045126130978594}, {"task_name": "winogrande", "prompt_name": "underscore refer to", "acc_norm": 0.5185477505919495, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.014042813708888378}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_5.json b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e99c1be05fdbd530c79d66c4d98bec13bc897381 --- /dev/null +++ b/421m3b93b9/eval/agg.lm1-421m-3b9_winogrande_underscore-refer-to_5.json @@ -0,0 +1 @@ +{"results": [{"task_name": "winogrande", "prompt_name": "underscore refer to", "acc": 0.5146014206787688, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_stderr": 0.014046492383275837}, {"task_name": "winogrande", "prompt_name": "underscore refer to", "acc_norm": 0.5146014206787688, "fixed_answer_choice_list": null, "dataset_path": "winogrande", "dataset_name": "winogrande_xl", "subset": null, "prompt_id": "5af00ba1-86e0-421b-bb97-26bf58df52d3", "prompt_jinja": "{{sentence}}\nWhat does the _ in the above sentence refer to? {{ option1 }} or {{ option2 }}? ||| {% if answer == '1' %} {{option1}} {% else %} {{ option2 }} {% endif %}", "prompt_original_task": true, "comment": "", "acc_norm_stderr": 0.01404649238327584}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fb18c54d6c514d95f58dca41de2eb2130b2536b5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88996fae9fe5a452ecf795993ed833bc9cfb51fb1aca83dbc34e8a49ed47d127 +size 3987668 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a87f3d83c91603ad5e4db9d988691126992c6cca --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15b6df09e6c5de7ada04f088f2c72ffc80b0da2fdb309d372a69cbf2dd80802 +size 9627998 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4f73c5de03cf12633f8ca88b98fa5215bde764e4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db51c9a263300a5e6bf60404f165eb5d8ffc889155befbf85e1d97f65fe31d3 +size 11455204 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cb8c483071e8f5e8972fad53036a5b6e56137476 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392eb4df0b5ddd96fad424c97652d14c69152e25ad96fd3a8e26b5301a9ffaa4 +size 6650627 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1669da53aec72509cf5f6a4a5e14f371cae2174c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0304b7443e1324a0f644eec6643c7bbfeb56a3cfc3892213d2f45ecb1d7e172d +size 30299872 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d8fe3f0865a63fd1b968e6778336d644b92da4cb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:028146f152ad5c4900e858149c304de724c1a0be67f8fd754e24750ab3feb004 +size 8494067 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c03e67e0eee9dd989d491b7d19751dbb7af67763 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528bbe430c8d0d8761400c996d32d24489a3d83b84e2237702f11ae366a37579 +size 3390719 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..656c614157f5d7228f37407d4825e2cde9305adc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6352a45f4fd689fd556cd2eaee249ef1d2082654c80ce5cd1ad6cca59b16d2a +size 6699528 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c50eb00690431cd19df93349287bb311a422a4b0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12426b6458bf388a1e70e202b6c12a4735a59215e230981acd3775366525220 +size 4258242 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3e509eac190912e600ebf3872c12f402ab4a53bd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d6656636cdc9bc99c942685bd3ed72af6d12d7d6a65a68b4334e4a0169f3373 +size 5011773 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bb23fb176f51f8ee386ab9fc0ffe954e065d0546 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f868e23da45b37f0b807b02d91073a1319914e921d91e5975a9d1fcb5c9d72 +size 23292632 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f335386237024692f4e6ad58d2579bc5dbdc0f62 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46cce1cdf82b830a3d4d586f27888a3997411a26a9155e55bc2c2bc2dae8c9c +size 6548686 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5523e9f3717bca5dd943d7d9db95138a6ad805c6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376611a8119636c76acfdc43066d75d34824cf8407f417e006e5cea4ea86c180 +size 4104142 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c123aa148d79fa438c50fbe5ebd54c00eca49ddf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15e5cb213cf431ea08c34d796f04583993c5024631a1b8fda92582c21b483fe +size 3153549 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..86424e1ea30f0dc566486331b5dbf10457d892d1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e152b1580d1e49997cff8d9f2024b25dd291b56dded1910aed89207ddabd79 +size 8159430 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8d3f6437104741e1f5acc8458b04ee8b809a4303 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135f101f3193ce8b263711ffdf8727908c4d64e01884e9cf84c0243fcfccb6f2 +size 4812082 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b519f208a273da73a63938c83283aa9d10a70fe3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222d01d1d0d3c49ad0e8e56a66db9277886594e1260ae8c2aa69e78469c1bf6c +size 16751862 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5e59baa3d79b13f9efde638b81e299691e111919 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37d715c198b1aee9bd66eb6a3afec415018ce991bc14b9ebbf4798f42593ae9 +size 6250471 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b7bc502e6bb9e6045a86f41b942123aca318cf39 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff42c10f9c4f5fb29bc527ee6dd4978e91d2ef0e90c59426919321f3d4c29915 +size 3858286 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e02d333a4aa12713f893e7ee704aa45bbc18f88f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2426f0f96fb7e33e5c52fe040882db78e9863eb6512f2b4787d7875070746c91 +size 3807431 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..38a6c18d6ec140ac403cc6424cffab6c76436cb1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18204b6c8ba9127fbd12a9da162618360d7d07e63a76a6b138b87b8a7429e4b +size 4722429 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..adf76b9196c62e38c1e6123372cfe0d298a0a51d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668285304eb73f36e654161e3dee2677e5dc4116dfc01d4c8db730d7da5da07b +size 5616407 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..72deaa18621e9dfea2614227663ca53828a4994e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6955edf7477c3b33bbfed01b4a5f45828b036305ced9376fc35b94b759c5c582 +size 19537662 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..26c3828186411d9d053a4ce266ef6ebb63fb1c81 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84b3606d06541137c7523d670360fda2bd36ac2cf33d3ddec0d3489083e748f +size 7393972 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d304b965f8ae58a9103f1695e45afee8f3b3bfae --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8a6ca515df7bb3dad9f2ae63cf931ac34fc63b21631d6961f7131b0ccf419a +size 5057508 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..25bbc402e7642ae22b8eb4240985c7e8477718e1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154e9cf05323f661c4b66ecc3e0226efa1ab40477c818c507dba2870dd4fc34b +size 10826092 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c11ce8149a641ebfee6aa9374bcf37c95a299f96 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8d14fadf56f75e3ba381c3e3e30d55494fe16d2c65248315a1b14712eab01b +size 13802078 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..651a3b7e0ff258422c57122515cf8343c3694e8a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b39eea6b15d5829e5657a3d4c464348d07bf1aa4439ed5fdb3883ddfe962479f +size 8330598 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..64762a5283a192472e4494f4662a21a95cd55a52 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bca8d9ed8d0e1404c3196ebc1b4d75b0101654e165d69ffbf720e706d2591b +size 38812532 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e089f8675d43a7876e13c16e3372b32ad1b0d340 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94a48ae48658d3a2ed813f009f9ebe0ce959b98050bd4117e33d4fc815cef1c +size 11060994 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..059f10ab8aa570d2142ed60c6d1a696d1ddbfb9f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eafaa260c4a3d354ff7ece12597932cf2e0f11ee82c1d2fe10885d3257de0b2 +size 7952417 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6c8f04bacb3a7b25cc37abfd6fc98b1868072357 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19fcb49dc6fc3f3699c2d2376bd4b38742d32b41233d1c38c3ab6940456ed4f +size 27020182 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9a383670971d07fada66bd2454b67c29453eec40 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6253ccf2046d704f84b20f91244788462e282ba41278e80f8c63a746352e7e +size 38320896 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b7e93e8bf77663e281bc21cd31e9cdc642ee3248 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e235a1aba06dbe368cd8422acb8a9af61be1667191e3aeaf788d79271a2498 +size 24648508 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e6decb08564995c0517ea8dbd04752b40de7cc7a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a829f633964b804c653a50d00b15fba5fdee359a8e61ef497f6399ea2413df +size 119502008 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4235b208da24bba3bd267c5bc57afbfa4122e0f7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a041ffcf82c9315572b69972520b021efe788466402bb27edf1f40b5e16431f6 +size 35287411 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4639c51144fb3aff6fecd5c556124b3357882e1f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7753689ebadf043ef6e15744890ef45b026e1fca326e9da781e7b2cbcf603ca +size 7839806 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..91493950feac42d2b61c62f2d92227be78de81fd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f560cc0231185b42ef94cd772ee187393c9320d4bb5e08ffd24798025d836ea +size 26644826 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e502ab3aea3cec222e5ffd790008a6dbe42eff6a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:421e405c4589d87eb3e2389aa70d3101ae75aa40fb44c54fbd064c0f79b915b1 +size 38061526 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..15c027aa2fe92ad986b7dd7996f9364a00ae6a4c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52600874d40d53c5f2183237798ee6f46fc89330a1fd62d90c9440deef121ca +size 24582198 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..77a22d4926474bb6a8325be8406f5a644e565573 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f972684ca2ba4166cf52414ac5e91cdb5c0a6f85ecb851f25edec9144090ba1a +size 119798252 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4b83136c78ebf5c62b631ba1118a21fcefbc1caa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020ebcb35594e991e7cbf5dc0014c6c60ddc4942f1adf1fec48bdf6b200fd093 +size 35428468 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5c3737c677beab51140ada2b700ba5b598f1d2cf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d1ab519e96e0384dbff9b97ca674a22ff134379ed6c4f72078784016fd2951 +size 7722424 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e25893427ba9a3b5b296b7399815ef6cbdbb0fc0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4d41aa1a22fd516a9b8372087f49f5f5d4f1cc6e85d6c6f2a1acfa4e283e29 +size 13390754 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b1dd49f71539eede5daa9d6785a4b715ef5b00a3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae918568ec0be28458b142ef53d71a89c5b977a47e5ffb8bc649862e6d4ec07e +size 38249670 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cea423957883935fac878e855522344bc0a9cc0c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc75cf9e661d8d6e7b7c57115dbd63ece277cc99b881d82a0f1493235544d8a +size 24693681 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..eaf1a3841a9a9392f79dda03f01a2d7450f048df --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab9255fd927ef543c80b8bf05bf3af0be64f83d271cc9efe1785b2c8d408ca3 +size 120278680 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..71b025c4dc489284980f49e0e4c6bc6270b62176 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1255199720d6959b633c778abc123d49210376c728f1a2dc39a20531095cf1 +size 35572685 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7b63d6ef6cf940dfe6b21f8ac6f6f9dadcebe76d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850480afe361cb0a798b44a2badfc89de967db43a6f711751d47d94397efc7f7 +size 7611078 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d2b48b2ad59f52da692a533a18175d358a2e1e1c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0465652e05925dfe7fbe7a9fac5653ab403108d42be96a0a901f16a886a6c34c +size 26085578 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..26182dc378e6d1ecced289e65b1876d93cf83194 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b1e7492b8f0b86d0db9beff3e8127e9348f90987c729b748af8bff70e59439 +size 37312500 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bfe35e1ade61113cb90b2d69b376c5e2c1c399de --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a126add6aa77fe7f723784add6ce11ac75fb7e0adf9363bdeb0d2d3519ed1d +size 24115420 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..af29b8f51092d8f3d9b32d0daf2065de2445c178 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8ebd3f1cb9a8ade2be4719480268857a3a940d00826fffd40ab92876c3db6c +size 117539284 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ca23649ce277a89490acfb7e7a79cdc761c2da7d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261910bdbecc2f48b2ff66616368f60d9b77d72bf64cd94c1dcae3202eb4f924 +size 34784370 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9156ed28b0cb6141c91753474369760ab069d006 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ab4cb67edc69e244afe30233cfa94ee56d0526348b695a9f2c9e66f5bd0cb3 +size 8076977 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..56f77d8647c58f5cb561630786a7eb6c48bde1a4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c865b1f2107103fc6dceb6c8f84c24e7ba9f01b733b754b7fd1df671e266fd84 +size 13807625 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2e89a083aed7277626359c574af9ca005838c25e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00aecdea309e2e5fcf90dfef40b5aad3d0c7c4d09fce08eec83257745441c617 +size 39417258 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..37cf45d34bcfeda8b53e73c0ebe43c0a138ef2f3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3b92884cd2aedc69730aa296ed391662700970e1ba6470cbe7385509e4097f +size 25365368 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8be984c9dd202ff9828f9830870e7b341a3e735f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5309fe1a0109e20ff8eef9f6f08ebab6e3d77560342da4f1c90c066c0dcc108a +size 123334364 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5e789a389873192bc7aedf6a504067ea53516b81 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da6dbf59a8f1a64dce1ef45f300141f0a3f9b1738946d3639c233bd3ee7221f +size 36468666 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f1a2beb85ac857fb8cbec468df4192d6bc67dc49 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cbc9ad51863518c3ee4a547ebd27ae5fda3728086806b86cb5431afea8ef44b +size 993367 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..baf6e929773b7165e3440cac3eadc0185b0a5f38 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c7df069668e368599ff6ec65fc4a9b3b33abeb572df3d877ca6fa2425a4fc8 +size 1452544 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..008916e9286cda6c41e9070e7a96add18d5f8798 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f46762a20060a990b2218584800f575e0d00bba45e01efb3ae1068887ba1162 +size 1910580 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3631742c673cc630c914eb49b176f6998363fa78 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d69eba1bba73d92cf64ad4dc7daff3520f6b7cd102a6842e51dafd36ffc3d1 +size 2367706 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..635b75270c63482a5ad5ffd2db810502a66ccf70 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b472efa38d76b48609d5303901505753508f99e9779dff606a307a8420a81a +size 2822053 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dd0ad61df209db7345726bcd5c23059d6a29ea0e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_GPT-3-style_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25fa23a318f0f043f2e3af9eceead208a31131e7e87ad0acaf87e596b5cd7a70 +size 3278211 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5d65d909c2d0f69332461da69b4266f1d687a53d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e1a341ee7011c0617a5e7c9c7418204873997f4c4bf62b3bbe8c92a91698d93 +size 1203155 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b1ce878e0baca92bdffc5e1e95712a14e4725e7e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701bf2d17666b683084b60e3615d0beb15979b4cea0af420cfaf229c978efdd9 +size 1755006 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dff1444dc461501a3123f9c690c94346180556e2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f22fb6c4a1805340c074cc29772470bcf626143d8e768761c159e67b29f0d9 +size 2304805 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bae3a89c6b9f73131f7389c7683c7a99f096690b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7e351e70378713e67b28f203c19a28adcfa2f12c9cd48da70a8e77b8ab142a +size 2853579 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..371a27cfd0341d5ff5209d7dfc642702186c0fa9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d49c0953426dc555de871975fee4d29cf3bf55988657df59c5c369ecd70c4fb +size 3399041 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6e6477787cb7ebf2a20f7ee5a9d018531201027f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8fdc48442dcc66894a550ab51c7a8e1f3e8b8857b4e6aa3d5cb410dd3fdfd9 +size 3946548 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fc8b1c0a591320b0fc032b9492291bfcdf3dc4ab --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8262a19925b1265453909cc98f6c1f810595356f7c2b2534dd6e6fe2f27e3f2 +size 1008067 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5da65bb99cad350fcbdedaeaeda266d4f754e5e7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a9a7a22f813b330c535cc0e26067dfeedfaf0dcab33acda97dde31c8bc76b4 +size 1478566 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ffb6473cd4f48e9549a5625a7caed2a5594ebeed --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84541517883b2b40d780d3dbec9d9f4f8f9bd6ef82b237d9e7e307f0b0ffd1bb +size 3897776 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c83b225b557fc3de80ac4e07b0c9afbc63e559ac --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c031915d62ec24be9a8bdcedf112f3ef3369549d21a4230c0daee7e77c02b8 +size 2418113 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dccf9b765d9957173321177fd28de5f05e799078 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6452cea3dcb2722bd76c228822c09846cad7265dd1f7f92850835a8f299f0976 +size 2884532 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9a71aeda9214d89ad0acf836be947ba7f3fa4c77 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_can-we-infer_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8f0765291737d7054c385dc1d0be8d68ccf62b417a9ecf104ee007a2564039 +size 3352953 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fa3c73140c31d0858e1550e849ee15452f3695aa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4851d79dfe72503395b326ad2de66f579673aa803bac5c6a8431bb47cbd862d4 +size 1160874 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2a2d0fea04ff6163e789fc4cce1bc0d32b2d56a4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83bb7d884f85e5fcaba3c24dfcbfa55fd61427b95fa7dff5330b3e09fb7a850f +size 1668647 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b6c85c96772265aca3ae0858c4284ab013397507 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d20b20eb168c4aa2a8980648c97d39164d09600483536b9960ff36e1c5e818e3 +size 2177279 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a7548ea38e4bafcc2504e7554399b613c08e508 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a22e024cbf646e1d046cdf3a29a356e0d6f38b53e899c12f3b280f808cf62849 +size 2684407 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0b66fbdedeba16e72413b447e94550df00a1e3fe --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ff51453ef3d58d9acdf54dbf408faa196fb868776f365dc882c21d2ef16309 +size 3188408 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2a72db49d281955db1209780ec16abd3fda1394e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9eb6b6463c81e4e62fd49ee1a5e0cf1cdaf7ce301cf5ea0745d5a978009c2a +size 3694477 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..70759472768c0088d9a20f095a85f7cb1c900c06 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff76d10132de49c9dc6da191596d439b5aa9a82d6885fd2721f8418dbcbfd150 +size 1027093 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8118fd94d2a83cde9c92352246901ffb37e6d993 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72b7d87f56e90b9d025a04678351937b276163cf9f1a933c122f748e266489b +size 1503561 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac4c1f65ad8e2278dbeefd7d5707ab00186832a0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a654d4208aa37eac76aa90bf20a0a53e032055b5d50bd657c9a68ea46c611bf +size 1979886 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2171476efb08be24ef3f61f9b9b2d9d52343ade0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bd7bbda17788a601a1b02236be2ee5fd26a75134ae29c78a06a852f7808b06 +size 2455131 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..31809e338f4d4f857a54c37a0813ec250254d005 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52194f6038fe4fc3b37c3a64b8fcef2b884fb53fa3ef142218d987c437468da5 +size 2927531 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1c6da3efa677209198bdc5e15861cf86e37fe9c4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r1_justified-in-saying_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e379e27001e1dacd28c8c302f148c53016ff0d3f96f83c44da1e4f958aeaf1 +size 3401994 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..29387206b3d04f9aeb4f8ec0f3d65150455d3daa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67212f494f405805938dfa48315b546f94f7d6d7b7bd1fe4b002b74a2afd72bb +size 993804 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6c97a4fac78c3efc7e579cc2ee58df1ce8a6f8c9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026b3df63c9f5ae96d8b11b2ee6c37d9c5a98d0ccefbdc4049a2318f313b076f +size 1447710 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ecf50e332aad49017b50ed2cbabd5433a2800c48 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bebbdedf7c9fff8e47e31a8a0d45db5786a4f86b2a54cf8162d9118be05a278c +size 1900555 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ca992cfeb3e728e078dc2d3fcaba1698f11e2f5d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b14e7cc9ad350dd02a63aa450fe222e2e684e72651382e249e1e9ec14cf09e4d +size 2350217 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6396e8133f6e500991d735e3380e454fae4b0ea8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acd7b406b02511645e0c4dc1d6afe4f81483c08e5c01aa537cadee00ff7d1bf +size 2799848 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..783c6583a954549c64e2b206c4d18df8a5eb3ad9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_GPT-3-style_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67364fbf233335c84305068652aab8a8bef9724a3b47032a73076d7a07bf451e +size 3250390 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..51b91ccdcadc110996e11071e1b869d6ab209dea --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e02d9937e9509a6c20c405837ad1a2bb017bb622a7c03f6a1e9cf2fac157d46 +size 1203557 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..79b9effc40be6f7a0ec61081d035d801ea9e90ac --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6600d531936e7ef70031daa10256ab0157ee2e4db6c4008c3be3cb0877b09e23 +size 1750064 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5825b9953d023fc0d8ba918b90f29730005fcdb7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4897dc89473c4320f75034ba4a4d7d6696566d1621f0a37988126c8864445db5 +size 2294970 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..625f3d7c0f5dcb7ce4b820696a99401e373e0628 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55880bf4802d4840b521c2d823f4fb144b2add61396025b341d348e8eb0ca2d +size 2836289 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cecae192da37d0fe296b3430ceff1856a66e9744 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:921fa26c16c3a83a8a740ffd4fb9a1cf842811a8ea3f9eb3bcb8a06ad67fa84c +size 6754408 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d94e1f44efe072700d97128930e807c115ef33b5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a618c0091d2123022766878275c355c720ab09a0266a01d9cf1e3cbb34d3026c +size 3918991 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..00a39b8eaedc35a8281bb4c85c3d33f73b9342bc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34141aaadb990573a8fb786c070dd09396fe1f58dfa4306ad7d6d864799a68d0 +size 1008464 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f859ab274df91bf994f640d7b8ecf057b555e3cc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e76e4117b58f180f70ba2c433226e8f9a1ad79333b5f8e54d2873637f2ad4c +size 1473974 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f5b7d8c47089ee3cfab0523a80a140dc44f2fcee --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f243bce6123244fd6587d58c7ff70d584123f0a83e8f77ca9b9dc32d6aeb41ba +size 1939141 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..91fee01ade0742d08954802c2324f27015d3c336 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157e73a5f2ae1fd7d22410ade78bc41ab276e4b82a396e95cca063bad2f0c069 +size 2400803 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..60fec5dcc4585d09e884d994d58c5266da1c50f9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a15c29581078f3160e3486317dd93593d8aa8d6b9fa2e0365f598a12770535a +size 2862573 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..acca80e35e7a1c7cf9f3e37349ec27fb2b7dac69 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_can-we-infer_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6856d8369abe5bf03a0980d9c3cb71cc5ec7db66aa1b3c580128c034fc008b9b +size 3325315 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..35f09c50968d99ab9e1895922cf9bdd24e8c5823 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33a92b594c5b3b1e0ce076089cc792f4af0fdfbef71bcfcb9e0aae27cc28394 +size 1161278 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..02cc4d8e6a3692f51dae79a6e440318d6ddd35a6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3737da7224265c2db5b7bfa5c03a1719c6f94ad2d45312502d70995200e9386f +size 1663799 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..46d38b65a65c79e032baa15bb440e2f2f8bbaeac --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc5600f5610bed3aa4cd326c82808885f63b7e8a38023a3b8a99f43a1df1a435 +size 2166772 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a646215fd76ebb55378e07464cbc5f13e83cb87a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:902de47563c8f1034998ebfe37c10d41d6e85fbb5ff62a298d7f98fc0d8ea902 +size 2666301 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c66cd7e81bb8a8655730e84c8bb558b21f8c0103 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8dc0a2cb5b6ab39d57f727566666e17a626e10cf5462b63498d3f686dcf719 +size 3165403 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..aaae6b953a12c09e9436c9b384aeec6eba46901f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858ee1bb494adb301bf386d5f9de205cb8b75c1b03c12c49de7f254fe1e2edc1 +size 3665728 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..213b0db05aa0b41e513554983f8e2469812db461 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2898b4110ed1350770ab58ebc30ba92d2056a06e239d7839fae41128df30b944 +size 1027491 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..41262be91e7092f36c396e397928097ebd5cba88 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99b0769ff19618e1b4aa3d7122d82c178381b7649e7b1e0610a43b2e5086cb5 +size 1498961 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7c02e7fb8abe530e1536d474d97c053ab1dcba42 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a89b7dde786a07c22e9657cb10919d5e4b059acb9dc88e8fd7602121bba8fad +size 1970147 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..66dec5ccda9ff9c94718fbac72250a85461f19c6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060e8170ff9fec60351920569961075bb40ecba137c5f6f22c77d30e58093b49 +size 2437810 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a7cacf71a5ef12575ea027a7d7f6fb425969a4ed --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79806064165f5bbd92637292679feca7b67fb097c186d15358203873c380b155 +size 2905593 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..168022f7f827ccc9fefcab7355efc50c3e666260 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r2_justified-in-saying_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ae86dd005b864d6943c6193d978ebd30bce21e212aa18fe808d78e73078ff8 +size 3374351 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..82e9555689a20ded38973fafff46b6b1c3ebe7b7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:923d9745923ee73bd2a1c936648a91b742fc40addc6344a2d39652425affbb07 +size 1169461 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5819edcef10324fac8b8c62b030cebbd8ef0ea5d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca7b802924105edf6de81e31876412f2893cb89b1a9a31e1f1486cc803231ab +size 1699086 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..811923f2d61a2640f83b52a3015a5759c834ebc7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4460a9ee7539c14df3fe81ce76579a2191a027294c8465dfdbc5cabd5694268 +size 4434882 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..725442b9b79f4dc3ac9d508caa74ce0c8bb6a9d1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf509754f0d9154a05d8fa847af2b343f081e1d2ed44a872fb25080416493903 +size 2730610 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..94eefcf05832bb011fd0daa43c75597f61256d99 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a1941d83310dfae98072a30f168eb944c26db56cee457dc9add7b289a54712a +size 3248032 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a5a9cb369eb141a265fbca9d5ede4008c7949251 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_GPT-3-style_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d5000ab9b571e19be2d180feaabca51b9edfb3780b1db97f6ac3aa0fbb5a7f +size 3776474 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..200d1728d3776394263cce3f8aedc24e668bea21 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30a0e9663d06be34a629cfa385f1bbe2499b2a792083e9fa33a781163a06a0b +size 1421203 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fe3c0c77f0fd332fb2b9aebbc2f2949d79b9d340 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8436189e45f167b68f379e1b616cda810a1807bc1f8dbcf03908bfc6beea0535 +size 2061859 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fcf7215faa493b4f6e02942f3a8a37aebf78de33 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11b08c189e5d259a0d843e02cd234776f1e5e40930c988d445f2309699a5c31 +size 2690169 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..42a2d2d9218573f0786280f380defaafa02abd1c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876a4bdf23c90eead122cd3e0e4c9e5af4d36e1c83ad25d79c5e702129da9e29 +size 3312677 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e88a8741c1eecb5fe2f659830c3d1817ac8bc99d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f2a135b998aa041295f0c59ae0bdec73470aa0606900d26d42ca1f187e4a71 +size 3939525 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f04973913b8d2c3c2ac430d8cd2ab0695f5a055b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5927250b3231995fa5932bb8fcb8ee6a543790695bb0f8060869e686c84066 +size 4577415 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a1ff025e6fe0a62f5e1b506619669df7071acc4d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee7ba96466acdbf6092ac74a333b071723aacba0cf7ab451b541ab39eca0391 +size 1187141 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c71b41e756c7dec048b0c0cfea15c68f0ae78e0e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393e20e7e60e1720bdb17ae02e7814f720c9e08ce92a401ab7fd93070c334d29 +size 1730467 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b266c6d1e3dc8c02c3b8fd6eebb7b91a6013e992 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada6425cfb0d33d99caaf38bbb82834f25d91d4ecf673a76efe9f68c46437425 +size 2263730 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d2befe32afffb07954cab6bb8cc9e3a1c313b469 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49df6e33954a5d96809b8d9783a7558ece746c637e515a7baebf261c253455f4 +size 5582624 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..928ee443035bcc6bc34c1c89dc7ca3c1b0fcb213 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fdd5e910acf565c9f6d7c243ff1888c8e231042fd4ceec229ab500b39189f3 +size 3323297 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d3a71a934754ae3a190e2c96cc5779dadd4d0444 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_can-we-infer_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a09299a7b30336364534b2f1baa47e4fa52ca98c98ea21126ceb9e04609bc8 +size 3866206 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6d7fc17c16caede58dceeab8a1c0d07c326060b1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d72c171ab5c4135db9f33ba6585b4b4136d0fb590498caa56cfa95dd57b275e +size 1370251 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9d6350c3c037eadbad97ea6a2698f83d3e3e9f20 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fe709edafc14e80bc973713053c9e14337943a2d4e6748a077f646830a2a33c +size 1959145 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..de36fc8c6dc3b95aebf4e934a2b6822cd801f41f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2037653f8b551d52c2feed68388e6b02e3a14704b8fe3747bcf46cc0377fc55 +size 2537996 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a27a9cc33a3d06fa9822a2d3e6588cb2363dff7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc1789a451814f3dc9fbdeb719e58db14f7a674b82427124f28bd6860c7cd36 +size 3111251 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3d535e384f90915027e140ffb4ada5e8aefa551a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582c65ae70af9f5630c6fffe9a9c99a2671c8d222ab8b965a84b31ea834b6f66 +size 3688486 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..17085bb47851d62354eb5214b65e1d6dc8699803 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f2bfe05539755255b0fcc21e5f70aec0df4f44eb55eb312c27efbf5388dc266 +size 4276683 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..04731fb65ccae9de33ddf82520b787d3c33e81b7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdbf79024e491e606443f17864e13841c05aebd253c18aeedb7f0b4ffe57d01 +size 1209914 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e8a9efb61cc2607a250edfed40747b22dfcceac2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba2ea84699f4895b80913cf1a239164bf0a71b7002a2c091c9507a33fb5b0d5 +size 1760476 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b0351d73e6be3384bdae856358a873de90ab84b9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15de0dc3cef61ba36d1ac247c8fbe38bded26a5a0c204688c80580d853291322 +size 2300941 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..71d497fdc5be6134c892b6cc39519253f67edcc5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43657a8f8196d5870c81a5dbe0359a8add5d804f3e989976424ab3c1ac316b21 +size 2835720 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2d9abb23dec37d0044cf86ec6cb4b4c5877d7e30 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3d6303275dfe5206e3e466d9d32d0edd720655213277324f339e0959a5bad4 +size 3374905 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7e198bbbf4826abee331f3f6f96cb88c673aac14 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_anli_r3_justified-in-saying_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d6e2cfb7ec7f90a70da625b000f6ebbbe0ed57d549aa198ea55511e0e3cc50 +size 3925032 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4ed1a0c22123c3e5f7f2522ba581433dbbf82c98 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803bbfa24c1b964e5cc6f6a4d5340d76a3e1060846a45dfa48c53424a0e712d3 +size 1216777 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c7f1150b46f9abc23546c89be96df7fa49c8b7d1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d002c6894fefa98c1f667ad61fee3790971a41e863afe50066f63f908013e0e +size 1670632 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..11111c051872164624a98f3f2f109b2579f52f6c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0255286ea91858409680637364ba8da65a9d200b2452b95d79cd2c70b06a2f2c +size 2120084 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7a033458184eda7a40672348ff80fda1a376dc2d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d547b1590bec30830e9470ae52ab3520f71b795c78b634957e039b6048c3cb3 +size 2577615 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac45e01948f2b7bc856579a9806d187bebd37b1d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec657cf85e723c7eaadf7a5f028f0674438ccccb238d4ee28137771028139cf +size 6055034 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fa3d636dcf16b16ffd429476b437752808b0dab6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_heres_a_problem_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9ebc7bbf2113857698955145fbb74d2a04c78394b643a55c12ef0f0cc01db1 +size 3479076 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..28ca758f234881923f24c4a8aade64e4bf1f6fa3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022cc7cbd1c079a9ea1710ee0d07ba5d71c4fd5615f69f600d45e2f177edaf58 +size 1458541 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ff2da196ee7ab82870313bac65c81939c39f0fe8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2bc57e9cf7b30e98e63609eb3990704d35e2c0014ea0b297ce70e22945f2059 +size 1961270 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6ccb539540b4121cf703afb6bde9ff4b155fa1a1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076db87fb8551d59ccbad134419528bed08fde7abd888e3a4e103bde4d5c4ddc +size 2457624 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ead2b866d0b5fc72b11fb7fe10831fe86fe3eece --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f972d065bdfd158cd89cc2eaeb8953042d03d305f636e8bb3e9f59df16eb4bc9 +size 2963272 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..816c89438b79955193732b31f00ccd93a84bddc8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff72121c42347d0342836c096eb5437e88960cbb2aaf095cc8a5f76db2f315a +size 6922318 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6b49467501a8fd14656ac80f053ba54c830c6424 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cbeacec397c2a7035627642d89c83aa3aa72f8406e7a58602ccdc7dc444b861 +size 3960358 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..684a8a1f27803e3601950b83da7ece348b93c4cf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:037f13b30af221bc089f521d67f03a5bf64d610f59a51d891be08ea3b6bdea6f +size 1506042 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c722b32778bd4a000b01dc22624c1f33f919216c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f32ef72b8e12e9df7052f3d2b5223217a01b1ca657662cb032aeed7bb1b9eac +size 2033072 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6cf38cbb07fbea47919980f4ba3ec09e3b2747e1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b45f042c9df9133b49194ab6183c94f1e76b8e2fb300c26519120a5739cc51e +size 2554202 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c549d61ae2650f7308961938968e6eb249363d66 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7920a14409e4e2cd8f1c1fb22c9e22439070a5261ec07d894a5fde75551b673 +size 3084540 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..290a36c53ed9c490bb88daf19a8c931c6b11bf73 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2d29e84d4f7c3113c8244a522ec66e48fc684ec8946b3f84e5f13a456cd211 +size 7214082 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..07c5f252cff565c47a4de407a40b8a8cbd4634f3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_multiple_choice_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80bfc8e0326cd9fa7ccba75219c2d0666d6be9a022fcc84f31a30372d8890b2 +size 4130657 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..82afb059df2239899d705ffdf81f2076f4d1ea29 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66e9f8e6f5ea7095ce05aa1ecbda3efc3c865390fe13a07e2ef806ecef4573c +size 1202714 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..47c850004e1daade640d92435446b239641c2741 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da3bf970d3526736006d5d333c226465eefeaa2549a216bd903398ef91c7f2e +size 1638992 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..69674be7b2ed60f3a6cfe2668b820f3b0e3c40e2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133b11c03effa78bd53619ab2dea0c14b2ca5db83d01a77b965bd5e450d3ba15 +size 2070864 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5906739d5c39c2715026b5068f3fd539d893c2d5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63cbc609f3989681cabd01b91d48a1121d4af7b9f9555d4c35eafa2f6263aca8 +size 2510815 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1186727bbaee5e80990ccc3688e0d08b726ac68e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e9427a6962bd42fe3c175a99d3ca96f978502e7ce3377dfbe66bbc581cdc0a +size 5886274 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6ebae07ea4ebb380a74beab54e5c41c9b3504faa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f1b492e4f66eeee35f6aed3d6ee0a7f624045ccd02bd568bfe9f7587a5b4f1 +size 3377116 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..35553f3ee9de19e20c507a11ff714883c1abc79b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dd1e74754ae0d560a6d6f51709b28635ac2bb8b9ecb1e501df7ad5419d7f372 +size 1187758 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c3d478a33648a02722e23764d0a705e161641580 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad55a5a7ef74eb40ac8fe9f96e613255c1518c82be79dbda62eb4ebe9fa65ae +size 1557832 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a23e53cec3cb231e22b462aeec6db6e669b5a166 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0c57bf51af867cc1c71823ec7279a4d32ab62bc941c2668af259f9bce283ff +size 1921743 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..82be7e603941d7dfe16c651779c99c0f5a70daff --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c909d5247895f2cc95c62937ecb0f7d8e925cfc4a9d2670b420c1a33337a808 +size 2294995 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3f0ce25b64e881a38441ca01407a3db01227c37a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088064b0fa7ba1caa9ba39d7d75c15407f7605f105e13c2b6d8207935aeb7f5c +size 5320866 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5ce0d8f724ee576882f6438633b2631d690dc7ed --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_challenge_qa_options_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc407b1f9cf030a07db0f972843b1288c5f7d2940ad5241db889b197cb45dff +size 3027199 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a4238a34853f17935ef8e994ae495e3808555c08 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a51434b11099ac9ead7e61ebfc4ef43dd549ed0817cbf58fa039b791f6ff4e7 +size 2351241 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..40dd2664d1383b62f3dab6634d50c97d8681a381 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92991e70a9c23ba0729defb5630014fe54c36c67009c9268e8ae4f5038c29c2c +size 3174164 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d975ab8c91d55799b0eb1c7117851bc4d53d7e44 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7856f3f5be20348ec619f92b7c00071992a0a0e48fb4a0da8ff232c85e430e +size 4008946 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..df36cdec3d356438cc3fc1248045f52db95acc35 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea92edb8580fc6ad1229cb6f7e658b7312b13fd12834772454125e633e21eb56 +size 4831612 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bc88b7f2e16b085d3e367204ba93d0e57cdfe87e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d0fe215d51c5350fa55378faeb24274a4e535c28e8d03a81204305009921de3 +size 11324712 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3d77d71cc4c9a2abc2bc5f94c6ea4ea27ec23596 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_heres_a_problem_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a36e09dccf4e2b2bab058a8cb583f1fe1e56e2904e37514fb7716c5379c7daa +size 6494729 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3467d219ec0c220a67ca135c89b8daa010ec0175 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440b15c2e669c2f3989fcb4ed996251cf212cc57f4145d4aed3456b74a5afaac +size 2746154 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a7d02022e877e451a70229b86c60f4326ba71f66 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e2c719901edb6d56b4920ecb238b82ae42cbaeeb6493dbf9de7d2e83c5b34d +size 3649055 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..96c5050f20a2c3bc6d34816ce51540471cfa445e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9930e0ef0182dc3c963dda4de4f44ecdc833980178d62634d77d54df91e586 +size 4566089 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c7a139bbfbd1896f82023adc7a813f55eb629f2b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4026e3155b6664de2261bacfbca7105db8d03dff4c6e1ca4b24d4c762e0ec47 +size 5469313 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..688d4c14bdb532f52ca3d937a57692fabd0fd3e6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebce411c2b1988565f4bd780d5c4c7873bf03cdce1f84847aa3c87e2dda72b49 +size 12763654 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8f72f94b9b632647015446066ef981732148ac34 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_i_am_hesitating_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d5a0a252d05c34c1909ab7424930bcd5eb0a89edc8983bf20d7c1196e15e10 +size 7294029 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1625c686bbb01830307f6ac8ee691c292f18e0bd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b11064d1db7b9556a5a028574204ba3a3bb31485756d0d7e2174f5f8affc55e +size 2843359 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..95c8db8ceaae363008f4c775fda74d54561f448e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd23b9d9354126e885cef0c9658563bc1b4f1813eda21ba8fd027ac0fb1f2dc +size 3795975 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..013b53141ee5b64420322c0dacc9c5fa8b11f704 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03aec20a6cac5df2cb98de8b4007f2eb10e6a48f8bb4fd07a388903fbcbdda34 +size 4763191 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ec7fce8a13e3d83f73da589c198209c50cee2fdd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e63125fef914f885de0932ad16e320feef2f3f0b57345133fcdfc943bcb4321b +size 5716063 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8a7c50db66f07f8e88eb0345226cd510571a09dc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae7b08ff0f3b1f25e54d260ae93dda4b8fb2f8375017eb60cfbf28ae27d8d22 +size 6678130 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7a46f2ddbbff7e9af8aed4411431346b3103a601 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_multiple_choice_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631e3b04f97b648a86f4c314665f6f4315f48c94ee4182f05ec6157bda3f8c20 +size 7640379 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8ddb97fcf824b0c6678ea1b0f6e40f876a9d5e21 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee656ebcef6a54c2852f56de78188991b420ef695031791b0658e18cd97e96b +size 2322732 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..802b9ccd698e98f2a322870c4915c37832069f27 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18614533fbec23eb5859c7efd100fd09a751c10ddf4253bfc743d00478d9924 +size 3110021 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0148bc94f7b03001e4fd493e8d7179356c623860 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b956827644d0b27b98c430eb195da6745a5832f608c21271863359628fb0e0a9 +size 3909160 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a849314ed3c4c9253d62df6303d18c90134b4eb8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b30c16d887e1c439b583b33d71553dffb93cce1895e925be654a0a1dcdd430b +size 4696184 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..49873ff8b7fd935849c67473f066e2f7c1ba6e35 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623c356ec78028a76ed68c4437c5536bdf79c6c5d59e852ac3a6796dec14784b +size 16473870 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..482522cdc7a46517f1f6a00235a2042231e8f6cf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab48a1b9d002e52e1e0177f99e87a040659033d1693fbc9720c4afb6587f2d82 +size 6288023 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f2d477d4019597d4bd0cbbaa3810343e35e2d044 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c4107c4b46187969ecf6cbce488b455123e8475a92023a81aee727ce1ead94 +size 2196982 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e2c856c871fecddc3afc23c15c6a05e6c5b71fb2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a05007f4d9ef421d1cd518ddd045c6afac8c42e470b7a7465a6c1f1580dcd4 +size 2831182 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..daddaf70adeb8f0a5fac13a00c420066fd815b7b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5482791466cee108e75af20d9a00676259f805588f53ed4b87a82efe0a0401 +size 3479812 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..44002b2634207343b1d47c7390d256462f4d835f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99762729bc31000de4f8669189d016692915ec794f7a6884e30bd35162cbc3a6 +size 4114433 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c22a7f6d90bc79c88a2ae1d5ac3f724200ab6f0d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66b21be395bd72d1fc18e935d77acb50526795ccc5f2ba3f3ea24b7a3100e2d8 +size 9516858 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0dbf83efbf29480d513d50288592ef053477009a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_arc_easy_qa_options_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca491faacdc93a5d778d0467df6dbe4ecce91751449ae2297c7a1735cabf3e6f +size 5402137 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d8b792f0f590c936b1030372ac8308a92b1a3a03 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5387d081255bcfd3ea7d3d420d53741dfa1924f1353f5ddb84ceefd54b1200 +size 3641831 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..10a6f960f5943e2df636164d761ea3802dbf22f2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e959c1c2ce27ed5b31fc5399a3fa5dd623591b070b520489ec272169e429d430 +size 5657491 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9ce454111a5c3a777c3316e2cd25ceb58c3a11e0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699d633f3881a499d64dc9aaa87877e08562b3e8bab870e00a717d36fcec2bd7 +size 7694591 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..41dc485426715cacb505225f098c21891454f8cf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f9cdcdfdcd5b4f92a372a60c0e4f98962db99716826ef2657b869809f33f68 +size 9728859 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b21d19d6ef3b713dd26d0be264f14cd388960855 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86b503f856f1e5ff60295d5f608cbc18d9ebad4aceabf1fc10bdfa9b951a7d0 +size 11769557 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2cc4bdc567cbf980fe00a3e8d06b1176b811fbdc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_GPT-3-Style_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9207d7280a39bab974ed8985818e1f17ebc1c44f78e58ae577d7d08295799eae +size 13791180 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1542437f3f4d3a96d0a294f24aa286d6a6afff21 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac68ab3718b67652d9e6b255ac3e26ca8856041135c263f4a97d75b18b7a784 +size 3984718 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a4907fa0f6fad03f585a5184f73500f6d6354a72 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e632237bb0a865bc37e5603264f03718b2e31e6cdd9270a4cecbaa6bf71d9c4e +size 6168138 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dfe6661fea45a1912f0f56ed94d6550fd439d511 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c2da750eb5cf0db6e807bc054eaf9819ef3654312e8e10941c2e07394b6e2d +size 8372372 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..864b1020dfdc8e447b7f3d46fe53ffd0dba34b9f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13c470a71aaca63a1ebb1c13d2eaa66b037453b23cf659bd6be14b986ad5b79 +size 10573568 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..810b0a4d9bcc150f2192406d35c52804888a8119 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f6a55bdb46d7d5657726efbac9a5cabf9cbe458c050e49f7391ad6acc20d2d +size 12781264 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e18dfaa7a3b85fe69c2fb15fab5d43e80ec998c2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_after_reading_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f950896bef90a785cbc590c30973a219a0b2c0cb7b2c9b94fb2c69f2f0fddd3d +size 14970015 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8638cfbf20acf042d938b0e39462f806876c7263 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c62a4d21f411006b64c01956a76c78b6dd90f94da193c3bde81ef8246b3e9fdd +size 4041716 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1df1002097ef7c2cb84e559e50f976ef1e7e46b3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5865ea70f3b083f5be81238f5a639717a600ef34b9a113101c0203322dac4098 +size 6261134 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a6ab7bff9998550ff3cb884771f693bae3251f7d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cdbc00cf6a6da51383a85ca9bba5cdd009faf75064a984864bec1b77e7f3a2 +size 8501080 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f02c4bcbbac170a2a1a7ecda0c40b73bf4e00314 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc74b8929a4b60675396e5e9ad6a70e3c0685dcfcc1614c556261396995b8816 +size 21476640 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..beacb18ebe970f4bb26dd7997a3bdafff61318bc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff0f588010f7dd9fdf7fe8cb55caa448397c8311e6b82a45797433ea67b5ec9 +size 12982038 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..02ad9467ec4461d83fbd81d8575230991305c91d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_exercise_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d8d272e8dc566a29b68f07d4f4b610bce91d5b4ce3ed3999244c40bdfc4f994 +size 15206770 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5274b958b7dad9d6482ee48ee3ea0ab1ae61fbdc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9563921bf281bc1c35b59c7365ebded2cc5f4159041425bb698b97146be5e02c +size 3665001 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..40607653d8af6fc963f22a1d27b7360b8021c805 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3d83f97a4784e041e18f3b040746fd7a2cbfbcac3b5359b685eb681458592a +size 5688139 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..90704fe08cc445076c41cc8a3c8f786689d6c47c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b10b04cb9b4b5316ce4d0e58e80fe2e5f02999fd8f81dce07290e8c52b67c9a +size 7733166 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5a22b818a0056a2d2bfde2a487062d70105c501f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a05b80427f3a3f5dedb9d60a073d830e019be60de00f591848e22e7bc8989d4 +size 9775436 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1f2c9b21cc350823a457839f466a947bb2cce530 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c69b8b98656a111e121505d357a18214c87ce943d03cd344ba08f53a5294cc1 +size 11824104 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c44e6fd2aa4b4c7e1b2eaa0c7ff19fcab42fe868 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_valid_binary_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f91a9bef867164eb4e76ea7c30f70161dd1a3b2253ef98dc793ae92e61c31d +size 13853817 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9640bc3e69c84adecb88832e048950cfc6d6cebf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a10ae601064d8b4386413a9ac20e0d2fd4ac123a56b4298eb6e60d13a9d03ce4 +size 3862398 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3fdb505520f85e1344d0c4171e85439778f303c8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e73cb53d43ebcb0a0532906a08828bada5f5d29550be5ad6e1f6d0891f94ac +size 5991512 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..728421168bd53de63f4d781807e6adbb1f3627bb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a357b9c05cf293b5a92825e2eadf6d3f88395622420b1f4377429d5b8a8de1 +size 8142436 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7d1e5e8c567cb16ed32bf0b460e5fdca961e8691 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36b10259df516968c1d693ec89ac2fb4f48da51ce0ee4a38c620307461e02040 +size 20581098 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..45ad9b267044afa9c2e3e6bd08b4ab7df67d82b7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:095acbbf9a0a6f7f16ac23b35f9409b404582045bf0b3679171bad45b2f91008 +size 24890498 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..03665061717616213bacf4003b9bb32759c3c3c4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_boolq_yes_no_question_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d308a5a4c277e3e99cea09b31dfb59852f8b318a02f4adfa386aafaa3baa55 +size 14580785 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3bd38c09d14be8bc2f5bd344c38ddb1c5650506e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f64ae8da0722d83bb557ae8d6ab757a4e597744c5122d72fe68ee49619ab986 +size 55169 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6de930e64c182b5889bdd9dce99635eda7d0bb54 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89de9ef7f2380acc83ba6b4fcd09184612049c628a6a217547280eba686a1c88 +size 77960 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..94945d563ad6e9f616d609d0c31bad263a9aa2f6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c75f191526ffa6158cb706dc8f99e15b08051f6017acbba7b248f903a631260 +size 99562 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..14788a2c38400035278f697780fb1e048c2fcc97 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671bbb68dec901cb1fecd06a9ca527484dc28362e63b30b89756700007331422 +size 120716 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8f2285ed6daef9fb326d418053bbbf2de4caba78 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050e0aadeb42fe684b131c266a4bb7c3502ad2cefedcfc378488c7b43edfad9d +size 142838 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7b0b398b082d7dc2865d6255b135d03729bd6adb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_GPT-3-style_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0460504ff2adf6bac6d910fcc25e6cbaee99f364d0a3d594464332c2d90cdf +size 163662 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..806b11a9c8b43716ddc929108e3243bee2b45fa9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09d06d81d146b2e5697d769fd76799731df2c2d70081347d8168f300891d6b8 +size 66218 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..05e727f552de7c8f5595e084f9c4ab9b04849c03 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9c0226b8c01919ce546dc31266c1d747a99ddf5a4fc3b08918c855832e043c +size 94141 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..461f74b961628ec1f808c064b49650a2213b9873 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e884d4364c8cf8327d67f58ad89bcec7f8c51a0aaaa61afc315c4aca5de62a5f +size 120835 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9f37659bebe1c95463693f4f3204acc524efe1f5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a4f79e4371a1e7a45388d8eff1a3c032203079bc1fca5ccbf84798c7e42019 +size 147065 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dc7ff093eaac0745145f026e7bbe6b32e5ef2724 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8e774fa63790745c071bf074cca1f9645448a9a45da8fd13bdd3428bf68a4c +size 174271 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..72e5b126ef2ff1ef8435445f194afb4ad00bfe67 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_MNLI-crowdsource_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61f88e9326c0a77061b2ce544640d019471374defb3d39c2b2cb9fa8258fe28 +size 200176 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a66d5f59d1f9223cf8bed7915b185ea64304d55d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff2e5f75762a208b1cbbb641f34c27d7a2249c0320d1f9f0db5a7372b82c04a +size 56307 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..49b8a66597194ec3e5084b5a77c2819b84130605 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e24210e9d4f342e4351917ff121605ceece75759cfb2bac8794865b42d5ec78 +size 79775 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..09dbdc3a7dad8d9ae9a50c98868ed01e89147bfd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fb4bc915d938a987dd6f03a631eaf1ecf4c897b99ee92b8a91cc9e3880a6920 +size 102065 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8a1469ed69e651dc1ca11313696fb2c1328b0d32 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33da3b35553c11c38296ab09fe9559dbb83eafecf4a9d20eb7a22631bc52f22f +size 123885 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d4bb5b4c70615754a2769f3d1d746c00a6f55ce8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee580585b055bc242e46df3dc6f9e5d102bb40692128e8670b4ba83facc72371 +size 146672 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d2c00942185a40d7d31ea2cdafe3e18257b24e8d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_can-we-infer_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c95854a670859219ed87564199f6a4e748038d07842159da244300aaea83450 +size 168156 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9911018d48abf20bd46750b9b35a96a98892ba5f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:871264186f9e5bbae081360d20076296a955332cb4a6008219e7044fa6d9521e +size 63963 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..359574cbe38cafff662442ac82adc74eca6d9ab9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae71f03468e292dd477a7b0ae2cbc114794347c14c8b24b2bb874d06a111f761 +size 89654 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d900dfdbfcab24b4bf251703e4f6b138914d5cb9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bf16acd7c3213312d9e50fe3281d2624c522cdee013820e95fc36a34ec0f87 +size 114141 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3bbc3f6aa1497a59a00f288581b41c6a8fb76c96 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eac59268b4dbf255a8c68293e413d9077b1b5f8c6e90d3f8acfe1afd9fa8920 +size 138164 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bf15d9fdf7c082a4880baca791282a14d252d6f9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9668f036ad1428520f2325f29e24a04eca780e82c631a455f1d2d3fc16a905 +size 163156 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b78b0837eea77fd8749cecc78a99037e424e4010 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c6ceab9ee380e7e76a3501dd44338c0288cc87fe8ff4272981b8348f73bf02 +size 186832 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..acaa9216c77902a0a1cacacd8e0fa203dc31815f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e029be952525bed49ce41f72cc670c588251951bb336db894e836df1bb27920c +size 57324 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fe577cb039354bba823554a0959b156370f8145e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9227b7943d96cce654c4cbab5768887a13d3bb026b5d08cb074b54c8ad440006 +size 81119 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a07b8ff075312bd0b9af8f8be2aab288168278da --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3b246aea185e1f9bb30cf0eb10eab65bd486af7729decd8d65433217996274 +size 103745 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..515ead19d90510784395af662a861635d0e36751 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1caa6a2da112afe9c482aac67251264b171871c65da66059ab96709afdb401d7 +size 125902 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3c30731c89ab37de7ae02ab5aaa668cec1ad0ccd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a893df99b6c81983d017d7e41b382ec55f71214565f0bec2f5321d3f4dc90a +size 149026 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9f2109eda42e64b62a0e62d070242b8e09474fbf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_cb_justified-in-saying_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f5236a07e03ebc16fc1e4c56820079a51dd486f12e7e43666834929c7cec46 +size 170849 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..276282b3c629416f62e834041d15bf07c93c620c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53f9fe96caf6f1bca5271e9a89746993f6992bf542c761688043181138dca42 +size 92210 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..75734cfa8802a740c86c83739aa1e4c863b1d72c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98591a2941d63f73fc09df93ceb5852d852e6883acc61e7b4f900287e2ced927 +size 111575 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..293c7714a632bee6d1d9e625020dbdf4e115811d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9db0e8094cb45e454717fa08da76fba8e18bc8ed7c63ddcdae447225a72dc8 +size 132058 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0d3c9440054440a2b1a5c9fd7475813505e631fe --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4857825dcaf9a6212a13a8c4b89a63643483e9afbd55ca49b0996e78021a0a +size 152205 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..14d4a58e89898438d735ea5f5e7608b49f3bbd90 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0469c40210c52dd18340dbee2ccac5ff15d5c3c45e11e3cd11106c1687915d45 +size 172031 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ca9e75f41099cfd4c9ffe7740c981bd6d9512f6d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_best_option_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ff1244c90fbbc91a45f827b146964d77fb558b3b90853c7032553b1e7e3dac +size 191974 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0eb8719f15e6e6a7861957bc7ae9bc6b829ff615 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9f47b8b40aadeb1f886f49c5f07eaabe9d864f4122a80d1a1a4cc03c6c0248 +size 87834 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7e81262d815c057421cca75d9ea17440fcf41e27 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ee2039ff669e35e8e0acb05af90a9427b8f8961b97e9befd99d741d9d52f06 +size 105024 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..aa16e9052b3de0c958889c7c7351f165354332e0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be977ad36b525e4f5a9df3b0f0710fce94f6cfa14365b7451ff5beda25f9c156 +size 123386 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f8c4c8f36d43cbb1c1ef6ea0e5a188f14e0d7e9f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6a1712a83d5c547a7506ac2a989c46bda95d4e5cefed8bbe1541df1457e5bf +size 141390 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0d4804ad0f6d61dc2933775ab6d18b05b60ea6c4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f569eb6831a7ee719addcce1d401bd7761a267b20d72bfe4062f5d0ebdbc8d29 +size 159043 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..76eff7939db955cf992de704be4768cadca78936 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_cause_effect_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3e79e34772e432f9c7168cbf95edb5b52d61fbcec0fa30a088d24b16eeca427 +size 176856 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8454289542fb18ee47e46f09ec9990dd07bbd6e9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6755cc56f5f4ada254c7aafa5709a3cd9f574560c646f6b730c84894fd355577 +size 85164 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dfe237a7b57975226f41fd4d2ab66231fd05d0a4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28aa139b79d8b868ef6ff729dada52987c598370cef132f34b069b05ca794ca +size 101224 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..85ccedca8b4f169e2b058c93fdbe78598feac711 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e860378acd95c1954cc3ec3c1b2edd6116e6a4114a9b6dd4aa7cb85625d60108 +size 118441 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3673013e4405283f23aa29bd45bc6ce056cc644c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2209d1f4f4373c75f205cb41f4d729f4a8c97e0940e8d981b749d373fce1ed6 +size 135360 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..58ac9253cd8c5f0fc044286fad0411e0089016e1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b8f79c7621fdba55786a91466856a10e4604fc0d3cd57802a95b03c77df55a +size 151909 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bc3c2bde55e173ef6478c85aab59fed481a06596 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_choose_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:415d7051b562e6b831dd3e40a9452cb707343cd58f8f3768edef7cd1cd3f65b7 +size 168701 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..575adea8012e8a8a78375859d6a39e085d1bd6dc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6badd41b425547aa7317f9d4090003b01021d600765945bb377a7b0444c55fd5 +size 96745 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a054c9df713c774abe8f579d7c10cfd584e9fe24 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc9f93f2cb5f523e431ed80cde731c9e38568252dd918622b71edcdc69b3fba +size 118235 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cdddbcb71287f327aec7b78102e5198032abf068 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5842723ce42de37d78f95453dea22fbe9491c0b4b22c7f553bb1cf7c3e5b77c9 +size 140886 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b30ca9a3fe5037dc039796a8cdf10499b8f9dc5d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daebeb663fcfc7095dd8a2c61a02826fa6393f69164a4dc01eda632c53d176e4 +size 163208 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..07eadda617d9f0f326cd774dce2a2645a1d9ab78 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2562cf44d5c5243a0a179bc022b2f0946c3ea9436df661e5708990173f9d49e2 +size 185155 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7456d5e3eacd28f6675c28d7f5c5b587bbd7c380 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_i_am_hesitating_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6562968a31e382c4c892cc8b65b9506b9d2a21a61f9292b7a87b473aca06da +size 207277 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4d196c460859f271d546e306a7571c1d7fc7a477 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87934de3e5813e8f2889b524340293d25e64dfaddecd93deda05159e900a2b09 +size 95758 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c26099fffd0d22e0c3074edd7f940f49c893ec38 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7be47d1ae627ddf6f55d517380fe3c24b90742eaaa10184c4f461a3afc2a0e +size 115611 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cba9255c80628653dd7130cb89729b53ae34ae45 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f5cd660ae9d34c3196d8734c652da5967bc1817cd9e17c36a7593703830c2a +size 136647 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3445963cd7059838df016e7e31ab1c727d628da2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58adce8290cb0d2b4850c2c156abf4be1104fcc2b2014479552c2881de26abc3 +size 157369 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..07a9968f624bfb52b85ab6e3a49c1194e23472fe --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e033c0963b5da380162feea72d0bbd35127952a9d0b5e9b0401794cd87e14458 +size 177724 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4187c7e083f006174f376a9a78a63a25931173aa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_copa_plausible_alternatives_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba7e46557c63571cdc91af041cb983b5de9cb60895a5eb2d1dc9b5962329128b +size 198311 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b4989b417ed906f71277f757993da66a925502fc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96fcc30cb89de329fd3230c545881e2ff18df672fb33274519b1fa7a0f61da6 +size 3648135 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e94ee686c7f52cc11563c4eb6fcf7eb407241f75 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a369822afdab708de31951e98ddce917c46144d22ebab240b893dee47a6533 +size 3944563 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c99ee08e097382acc877e2c81a121e318b9a64e1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df83bd2c5a179fddbe5c039b4121eb9f92bfb3bc7f328137bfb07b30ad8e3300 +size 9849430 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6db31a0e4f5abd8bbec7124bff16aa81a58d3852 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3654f51583b5a613992cb7e57aecabbbce85c108794db043ae4b027d34fb2e1 +size 5874027 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7d50692a7820bc28a6ed39b9ac4113970af559aa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebe476f86b356e8cc1a527ecc1d33871d381634c36bef8a6d42f3fea5c41a84 +size 13630336 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5e0816645899b52d05106cfeba8cdb2f186f69e2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5031b6daf7133b0655102dcce7257a97211363c42c898b3e1e3911ac86091881 +size 7758770 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d830640f95af85b0073fb4a5cc6833c20356d04c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf5861a4bfe415d9ac14104891ad567c48c654b4b5a40bfc7aa7199c78f2d29 +size 3330122 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a157be46a186157b36ab917b1598bebaa3d00f5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f928adfba197e7d544cabdf68511fe6ffd8d9a57ef06b651ca0260e9e3b992 +size 3882608 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4f08bb8bd1247669012a7b8cc197780fda771611 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d4fb8b955f5970b4c9e72ea2d464c89e386bab5d63c5feb460777845f108e6 +size 4829023 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..83f4107fbdab834050b6d4555f0dd33a9f8e08ac --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c0b22b4e1799348d068fa28a471073e2d1add900eacbc01c98736ede684824c +size 5750417 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..41b6e702588ed48187395d3f46708b4e86cd7567 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b338cd2a678fca8d2e889cdccbf63d1ee2f898a34b4ed2cfb221658e0037f1a +size 13323016 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..811a87b18454db2a2018419d0bb853e89353ad22 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af847fcd60c3bec97378a078b04caed4c0257eaed193037cd7aa214344d03c44 +size 7573884 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b1451d2ce6538c708e3f2cede9967195da19d116 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5893d91f8e155b9e4f58cf25239c8aeb0d100463f28acf0dea9d1d540b7a701f +size 4110633 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5ad79d2041deb96749ed640f00ca2f89c455fa6f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfd484454afc018526a116aa23e57ec38e76cfe02fede8e233d8b090ec2bb9d +size 5126874 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d0f3b811cc5bfc18b562724d65317f2d5f648fe5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a63b35c4d640a54120e4ad3c608d297a014bb1282f6daa42fd40c27901c7fdc +size 6146963 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b5fa8e7c8d3f0124d572b9aa67d89e692eaac7fc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae407041d498bdea172d96d14e6d214917c5133c4a239c01533ea1211d1de9ac +size 7167719 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ecf5d6c1aa828c157fb3bd5b83b5ae160636122c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c10b686f8f44e03d041aa6baf50c1247e7bb7739de3c63fa6c96667395fd8e +size 16387018 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..68181a2b0e6a0f582948a0a0ff3760b344a68688 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bfdd1a36752813273aed1896da48f1d4ea9942bbd7ea31398557d06cb76c7d1 +size 9232932 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ed2feb7fc247c1223b472f1cc61c854954ed2d1f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4333f6793cf6471e3aae23de1b488c1a45ddff72f89f093611a8be2d666e734f +size 4164910 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c57ffe845776bd633b6f4fb1a95b9735593e8b9c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9bbedbc6b532729cfa00d8d6a6f4c13b53ddbe744c435a6b430c0e01b3449b +size 5026605 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9901d3240e211cdc54490d65d5a740518a9b7c11 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2faf7086bb5c0e7daf73931f4df449de0ad4dcc1a0e93636ef14501552367a35 +size 6112435 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4104ff1fea465ada2bbf2a88bffa349e0e30bf25 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17236bf2e2abd9e3306ebe3df4899e218c368233059d13c8f0dd82a18c74cc3 +size 7191042 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..134ab494622f47502065fff0981df7f472968890 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119a419f0460e1e333fc8656e6bf4105bd86463bcfd1bc80a47d94e642c37bb0 +size 24800061 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b40124c0d1e660b5ed7fea1183a3c310c4c0b53c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2e42e4edf390e1f9c52dc375acb692ce6f3258c26a56dd3d13ca58efd9dcbc +size 9347006 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..43c170a87e846fed620855bd64424f22dfafd7e1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc44d997ade23b1d12d3f59fe05adc05b2403635081f6a02d5e082a04236c3c4 +size 3196541 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..abaf8aff14c81c6b5260dc0170b0986b706c7a5f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bed68b5550cb0360152a7d3d3a124a578e7537f4f613865dc84ca5a7057799c2 +size 3505500 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4b6ff39259f23ebfc9621afd673aea1569282579 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5751dfcacb58c51af3ff2cbbbaf3a2b1eec294a30541bdcf459edcdf257e27 +size 4298598 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cf820d6077c057ff7012c2e2a40d44516c2d16c7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90adad5f2f86bce7f7de0937a81b8ff9b286803048170541f035df8ddb3a6ee2 +size 5087457 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8f1a8122f5b070ed272fec0a97ecdfa54f642832 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:170b7432b51f02407c467ec90baa34b0f68a645e250593e5476c6dc598d89b05 +size 11748752 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4d746852c9330ef7a638592ede6d7206a75c65e5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_e2e_nlg_cleaned_text_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6196b6d917d74ece2b2a7a84ad93454245a909ed86c375022a9b6d81b45f4e24 +size 6664784 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..03bc9bfab4022f77c573d056aeb094057c854942 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a9eefd29271b1a91c4569b64afc463c354cd61260437265a0aecca6dd25812 +size 2880423 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..711c92a348b0af5703368421302ea1c00bece064 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9524cc979f31bc50d2764e2e853995f76f50671523a8e919fe0e1128d8debf +size 10227928 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..99318e7aa87a1fa9b93622165e2d57f6da389e1b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af1317454531f252f17c333aa657f0bec93408b42e38d09a2c5cb3752fa51d5 +size 14937424 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5711ec27030cac6a4d4911594ad58064489010d6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c75ca7bcede246cdb5ba89854cd884bf3a23e7b7c3b4345e77c1d3d6368024 +size 9769434 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6dd72a2e1cab429ed063b42bf3f0efd6f7ed629b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611388dff7a3dd48f10adf362fbf6ccd1a362a78ec70978259f0873f80250c1a +size 23645460 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cea4170739324b46fca1d4eeb76560dc70310ea2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33dd6259a18fd81b17d583bf536d6744a06f0d75e1e00c49e4c8bfc9c10c665b +size 14076795 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b593da61e324f3614f02c23cc0fae0893706b5ae --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d11003c6fcce4ee4808610bfd8814c74f08f7505007c4fa52241245247ac1ef +size 2783621 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9cc8d603d7272c6f9ed3dfda96bc69c9ae82f97c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3968f74c932c91716d880238951f83f6619badc47b8143d0b2920e1ac3219710 +size 4920662 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..abf196bd7a8874a12ba45215d3c49384a05d4bbd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd086d6d12837d433e1bfb54f8384e5f9d271e93a182777399a499ee2362d332 +size 7203219 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ede78b2912f4002b69d5047d6a87538120e2ccb9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3656437410576b9bc1c094364eea2b1ec30f93fb9879253c2a8d01c43b484a8f +size 9473492 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2463897434d5dead400f728b40b7dd5a39f946f4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b0a72c6484c0d317812b544b81e7f61bfcf689528143f7fbeb5f893592850c +size 23125660 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8a99c8b2ea6b13311099437e0355d7d056b22714 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_DOC_tldr_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e668da62fe7d73898ac5738473d14c1f0b2ba87e40de3a2ce90bdf1f22b155c +size 13794812 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9e39650dc8f198ee8c3fa991ab5398480e4c5b28 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563d2531a128aecaafada7ab5a2f5e7c442ed1363fe3eb844b010fe96783521c +size 2833675 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..216ddb640fa9beef5972a605b5c3a073bfe6e16f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce144b15fafd49f27d72409c2fd8b5f185c45096b157e7b2c1a7a6b5a626563f +size 5068999 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..40af9f1f8d647c90cc954c8eaf760ff06e09e560 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8f72041762db6639e911ee0a0ef8838b3bcabfb46be72c9a44fa01c522920c +size 7341397 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cd4507d3e40cf92c08e5b682bd182daa32aecbd3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc671db3ab6509e531579666bd05afcc773a869328a9db15edcec6377dae1bc +size 9616711 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..40b65716663953c8b85aa293569c6452bab25949 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22336a1393813fdbda0fd4b3a3cebbe28e9f8ea25e9d6a596debecc83e90cf69 +size 35003235 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..23c09447c9fa031a32a7751f4b07916f4d126fb2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada5ec2417312f4678850d91f29ab204fa7576cab6a4af4ac97c307db1aabca2 +size 13897500 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8d1f2e551ec9a48d98858b29facf21c308f09e8c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591efb03b9dc5d65fcafb3b8b800a46608378406af930476e7eb4c4e6761a3a5 +size 2822426 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a2f4878c5d2988509994e670ce19e9ac20d543b2 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4885f5390089ddfc4c2fea2425a6750ba5af3096a9c47769673d26d653ab347 +size 5082546 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c11685134f7162fff205b636b5b5bf7ef91cd751 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb21bcd32cd6f323dd87dc566965a641de08f30ecdcbbd5fe9100881001dadf1 +size 7361083 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..50f8bc7df182059dc5328538340b18dab738f420 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e44a9a2d5d7378a6c099f66a5f3bbf65a4da20613d206c0d8669c6d506292e6 +size 9630090 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..135d3eb6a4d7ab7df77800658208ddb7bf13aa98 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c4d76a73d50b722ef931a35fd59fef9b642ed08cd28591229ddde533fbdc5b +size 23314800 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f9a99cd9f6f8b8a7b91f74fe5ebf63081baff0e1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_DOC_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affc60715d879429682269a988983e0da178195cd642fc8d952a25f91a508be4 +size 13882410 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..afa30c4393bbd8312d209746e2427bf36dbeddb9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff32223e5de6bb19b77848ad5759a09b2be683d9dd3b6c895e036e0187802ddd +size 2872768 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..66c255b8b38311f95dad60da84ae9cc0a6c80a03 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d62140cb53ad0d3c2b06d9b996cf088b17e059dc236c44e7153f3620c332cac +size 5131088 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1d94e0408620ec0168a90fe3ea7fe8961adda590 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178f3072ef88c713d0d391716a82521de99d12dd7d64769862eae6c6b6990b83 +size 7422234 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..506b1709522f48e8a205be4ec96cef4b13597a97 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c98f19f27800f9331609c0b804b4bc381c3a62ce996670e736e69a79c8d2f23 +size 9711980 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bd01f251c790e8d05b0931d394a25da3ecafed9d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5962802ca9baa7809a1b1abbe542609ee313380fe3fa600856c6cef79e03785c +size 23533046 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0681f8eab96b9b7fe9c00cfddd7508a370b39810 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9ee928c3c5edd50c177fb310cd3602c946466442db4f62df95aa85a7c1fd01 +size 14018650 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..30f7134b4b4ab0099069f2de75505c541d53c419 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b336b50cbc6cc8daa04ad977c8d26a18005b5c8edd91055a170960e1e996a73c +size 3426122 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..336626462677483256b244423283ec3b6ddd94ee --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd135574831a7ad494e7cded41427bf4dfa00a5f7e6e683d321831bfef7c1a4 +size 2803093 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..43cc4485b0dedc72e8e550533152a73276dbe501 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abeded8f0b3f8e12fe5348a1115f88805dd8a0793089b9a8dd2ec15cfb3c6ad +size 3547911 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..585db97a096c20b2b2c2ecd5257cd8dab79d7677 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9807246fffbd5060e0583685fec054e5bde8382baee23b88d6b54b7e412323a +size 4199691 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b82c96a190b0525acd0131724dfac0391b931028 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1486f477eab4fe306add5cd38543a6d0dd203a5ed00343826899d9833dfdb48d +size 19458588 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b6aa8c7d4a568d490fd9bf86afe2fa24ec443f81 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_Correct-the-solution_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bca0ae825f3c4e0a2b3fb34f5d550560dece6252d947e5bf9d89e6b1d13fcb3 +size 5534050 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..49eff4624c69228afb75a141be1d956c82001ce9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa31be1f22fc078605cb4382f4a6e288695cc5a287fdb633e5f5213a5d1a157 +size 2115935 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3c482c3df9decd346f5fc00abccee2b98a02e3ee --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bf18b2f511bd1d461a4f115da409b0aa8d1d71c9f6a47fc844359cf871a4c1 +size 2900909 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..247d2122c1b325d5def3a8ea78a19f0143a06536 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f72eba61723734249a8b7b07d843857fdee3a536dd4d019d6896565a50cd299 +size 3683911 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9ea27a0a67af1632e5b7901172dd0fe5407fbe2d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418cffa1e654a104e34e08e98b96ce0b630081c81483d544bfd50626eb39a1e1 +size 4458372 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..817cdd8783aaf5012cae422ba8c2a333399e961b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e8df69d7b3eccd92dad10bc04c3228662013261915fea6b185a820e19c2cae +size 15763548 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..084abe036d10b4a96ff8cde5291af2a55d8a6339 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793f3ceeccb7335aee32a6a41a19ca4e347cd0ca48006009330ac0f0264a4c32 +size 6040677 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..35c012edf3702b0285745178d85d9d6d17e32e36 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597dae71812ddec8b5fd958e839fff076a8b4a93e6b29b7bb4a11642b213ad01 +size 2801148 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..67fc75c35639ad8c4213beaca63cad52ae7ad2f9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51e2cb7e0d0493ab423a7ffaec76fb2343e3675ede18946e75560492f31cc1e +size 4272528 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2f9bac6ca0573e8b77f2ab3f070912a8b6bc5c3f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8160a9e966a906f696e57f5e010fa9046c8765ec7e6419d67eac4f21d17d579 +size 1970322 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7121698f80f6ac536dfb83af1c34db37770f79df --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6117bd5f611ca3788648ec3f01da62415fc75b5bdb8593d1532108dec0282f2 +size 2159965 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3fc3f853d9c8386bc9b262c6388635202310dd8e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eaa72e2e76e35bd5de6fc271125b1a14e481547bfc3b226b8255a5d0e76bf83 +size 9766684 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..13dc86264376018f71035b16dbdec9127cd345c1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_no-prompt-needed_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a3885cd4889b2a5ad53721a354d37594c7f203fafd86c54b5331c3560ff728 +size 2733242 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..db38eeae18cb274507f443e92f90086d85bf6131 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe6d1ec7b37bae5b3662ab78623e555447052a034a47a8948c3965986ff33ce +size 1864129 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..876c0e992634d7fb5a4b32f828eb8f96980a2e91 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:628f661cedcb80d7e652652fde065fcbf8ccb1e2e224524a06f9edda8582cb7b +size 2557203 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..168669f81ddbe239225a7b853c533221e6f13c18 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b34383cfbbce29803d5e19d1228342c87d3f7e77325915aab484b61355c064 +size 3248305 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c3851b3e74fc7fe02e3d721ae35a487fc53227bb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd99e21cc190cd90b487ec585233e4827789edd267f84d5e568dd9c64764eb4 +size 3930866 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..efe4fcfef2d1b1034741d094cdf54cdfb960e10b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e80da5fb2ff65139ab56d8e834a6a532e384f8c094d9adbed91780e26a0ed3 +size 9270220 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..82304da126f385ecaf0345b18eb33866e468b8d8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_pick_correct_choice_index_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5643bf0f4f18f99e64a8aa43d6bad757ab7dc23be01926e60b1ab636b775691c +size 5329371 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3c8b7f988079ca2e5034f4dd5c0e1b5d412a34b7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643b21501515294326d0bbba9622864a6aec2c6f0742e34689a00f0a31cff2c4 +size 2257595 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e1969a9d0e9f69a8f106a0b41a87e5144f1c2563 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a53e7e83d696c15df5aca7ebe620c5c0a89744b9ce2dfc583d550d48b47990 +size 3017127 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..50aef65de678eba4baa1ee7350675ebe33ac10a8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3763c0623225cbcb6d24b0f168c15ddf7a90ff0f8feea3d8829abdf62bd73cf +size 7546344 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5f9e677f24197a9d7248266be6e05613992f7668 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5e32daec3446712f9af5541b73e6886da81b47d973b296a9ab18421c665cbc +size 4518035 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1252c8101abcf7de58b9d41fc74c6508f42b2176 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9cee2cc0f19b2613ebee2bdeec143b96badf7cad9420d894d30f0e5aea9635a +size 10585284 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..08ddf0d353f54ef1541f713d1875911674f80c6c --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9145736fbc237033714ec6c8bf22f0e2b2c4f7d16417827dcf84924a7058b5d +size 6054067 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8e52bef1c0dfb6d4c16fe67a822c24895bb7cd80 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:442cc6497aaa97ca1faa4d794836da283f9cb16d9dca5346786734e15076449b +size 639649 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c1f5112b4182efc84137d2ab885be0bd39301888 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e898af2ab2783172b897879eacf6b810a8997d0df568f68602717c1135e61c +size 754663 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7be2ca7dd2073cf416762f5a4b00850727f23d0f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1439b0f47de6c7bf94d47852757769aab6ca0cb30507498dc5e9143149253a92 +size 870913 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e551f87a6dd5d8c3dc9f50e114623153efba4518 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6393a6775465eb8db88299156dfc21f731298dfb862c2625a274a5c5734ddd8e +size 985255 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f9770ac6e155c166239d06780677acd8d6684072 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85cadf0aff158a74c7af493f20e46a3d66cb44141b13dcbd2c1a33d656231363 +size 1098013 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a1b42022848e6a0aa6b007fa94727caca0f3b3bd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e377c5772cabc063b195789854a0bccf4c574c8acbeb580d0d9b461cd2f1853 +size 1213217 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..65703f507b7ea2230956bc17c489f5fcfecf87aa --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9890ed5a464c9a733946a7b75e1f1ac80542427d6e8aee06cbd83b5b649cd6 +size 1182214 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e826bfb27ab55a22ef49cbb07af200694e2e893e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a7aed3461d3bcbc28f7138624c638db6796078fd2f108aed02032393745f473 +size 1779079 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0bfeb669674d3e97e0e56ff7a76f6f0d5845e85e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9278f1352a7a596d8314e3ed5e4f7cb2c42a289c899d87f30f36ae7868bf61c8 +size 2388227 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4335edd2cdd5e8a990feca512a3fb0ef3e73c441 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6140c3c81a126c753342a7fb1dd14c2241900a6de6bca683a5d89aeba49a20d +size 2973217 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..27179b7cf8ad7db4427550616d32508570e7d920 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee73bd55a47b2525eec9ab6ee33904e3da802a85dcf77294ed4bffad0d1a3766 +size 3555625 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..57c05d7229111a2ed3cae5af2cd2299062f0adf0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Direct-Question_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38afe2fef0cbe4469197d67ae53da786a7f8678630010cdbb458d9d781c7690a +size 4144466 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3f57839f9012514401937b552f4e2cb4f16eec2f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1f97477a1814cfc8ec1ffa944c409e014ce61c79b3e4cca9d57d5b7a5897b6 +size 1328905 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..aba203cd4fcee5934e085579106c5a0c350273f1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8922cfea4d6859646098f20f4ae8081ea9bdd6b97f7157d268d2ca3eb0dbf15 +size 1524405 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4edc8e1c2df65e5af2899ce371c78269189a901a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df96f958a2629d99905ee57697869e520fdec222c55e46fb5b1a1fa9bee60373 +size 1720519 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..61967107598e043684e08e9014c46f60ee9de4ef --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae18355f5b027ef950b343e99ceb4eba38e3d8e6bd3a359daaa5c387dbc22e10 +size 1915741 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..37f8d5735d0f2ead3c2d4738280ffec9cecc7d20 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2308d387025527224081697f7bf2429d1a5e4ba32b3d40056ee907079c96860d +size 2107423 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b1be6f3615d5d4f35d060621f3f03b935f48a52a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8304f9bfaa6338e65a945a4dfaee71214dddf6460b9a7ca3fa892f90257050c9 +size 2300857 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5d8e36631ba93bf781fe1737485140180a581548 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96fe9ab10cc655e9eec2044e7ca914e6895186491567722031d97db010cd572 +size 1935172 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d59f663558cde1ae1ac8a12cc966a8bc678fd1df --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc0f07684ad895f7674f6dceca66eb21182935c9b9afa0452b8ecc248698644 +size 2636333 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..48598f8749d6e3058b329046f9b4267fdbda409a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73bb7297479a76d6995fc942456dfdcd2cf10218f584df0cac3ca4cb2461b4c +size 3349266 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c939389ec770d1bf79d5696f98925004253095a8 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e106765e79a93600257e1265f60390a0cda542080aa81588162acf5c19771126 +size 4038958 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac214dc0d767001dc13103bab315828eefe29892 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50807a48d7a927117ed46e86572c88c989266541db2d5cf9c7bee1bdd757ad2c +size 4724541 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e5f5dfb00c55d5b215ea6ff36b7d29ec6e3c66ca --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac6be8ca40ef508e71429e5d60f694a30efa43b7bd55777b57e69221306bd9c1 +size 5415436 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a0eb6fcf76f2bfe63062681234a95be56e79a0f6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a664b66a5035b927b13d4391f01ee43d11da5bd2518b0a497d3c3d0feda4b6f7 +size 1870049 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..759acf99cce68d0b743f885ac16a46ff3eb0ce6d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b112a04852c67334121fe807bdc54f07403562a2c1c12af9326cbad266f07e30 +size 2545285 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1b180bdc2d4b1d0bdd5d29d82cb76c129e0e3c5a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ee200cc2b4d202aacc22d85998e1e80763f9b3b76f6b49ceb0d6ce19981a16 +size 6464646 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..64df74fa66d369ae746cc546688723b1f40d9859 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55060562ee463d4605f7453dd64967d6f62ef191b931a55b804c6b63ded9f48 +size 3896064 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..98956b54baea9899e3af674f0807771004968f51 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26111f5b57d9572eff4ecda930d6124134a7311ca857222fec22f9c64798bf00 +size 4555510 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..868d92be1e85ea6b1f6d9010fa7a7c2fdffc837a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_sciq_Multiple-Choice_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3d9dda61a29fa7436875fb89e5d2dc160bcd5ed95493206b9f7f57c46d88ae +size 5220578 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5f401cbcc0a0674d944d236a4faea3cea323c416 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a82cf94ffa6d29e80d45bcebc38627408a4987e692114b7e3c2b9ad0c59102f +size 2212266 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..27b2f93e06ac9c77544ea3b60111fa02982c65c7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfab9438751a2b8e679dcd823cdb0a54155b6050a0c99facde2177a2b28cdcd +size 2972756 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d5d50e3417cb8e88280916569e0c2b02932caf53 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5700f3bd4c1f92971538946e8c95896a2c07dd40c6dd52a09400efb313cb2c0a +size 3725211 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..37a30868a804bc987ef794ba8009d9ea1bab7f11 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c05cf45ac1b25a921d47d932af5917c6336689e70b8c870d88059f8277340b36 +size 8953036 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4e42ad9d1b9054850caf91e173484ddc4bbd4e17 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ed6155267c1e73600811e9e8cf88e395e17662cc5dacc7357f9f6f22788ee2 +size 5228488 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..729465f52750b76caf1ca0d2f129c8cae5cd78a5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d970558ff4d6a2297e105612439f94051804ab9bce4ed4ea27ae08b5b2c4d5f2 +size 5979111 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2fb05c83a0b144b64f5415c15c2d4f2190e2fc9d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6cbfe158684c0231f2e6dd182cbc4f201d84b769a5bd8e29be54e9aad5de3b7 +size 2360121 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7dde3b719dbfb026a66041c9486e05e57b1cbecc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdc67ab79fd2ed70c661ff4b789aa105772765bc1485737344d7b5d6fc74493 +size 3191697 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b2d681169004f3485611ee149b9c97db2f5861d1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7096aecf50d143b8e7eabd1a9654cd5e46fba76ca166c5b638353f4c29dea074 +size 4015110 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c037ce81d7927de7e51037c6ab5e295dfe445cb7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1a93ad51636c2d35cba679466c5f48248a320f7f30f005aac74403aa218e4d +size 4837595 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fafc457808bb3b9cc29eb48f518f0bfb56431ab5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15131573df88e4748e649ac2bc781aaed187b652da204875f2121c8c611f438a +size 5660246 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..20dfffcf94f3f13093bedccd6fb10345363c9a86 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aca3f5d460340e859ca863ec015047e130cc648929ca696ac40ec71bf341dce +size 6482130 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..114aded58c877847565f849840477a783ef882b0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0ce2b43d69813b7a5884a50e94d06cbcb5d339d089cfe145c6f58a5d53f919 +size 1877860 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5137ac1aa419848fc1946144f870d38450ed0b45 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a683ede56ccea1155b5a941cf992b48db6a0ae8f02f83663a8b1134087266ec +size 2433614 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f8b172683ddd4d1a8995c3157fa9a5b34f977103 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc7df9b0cc906994959cecd8e059d5b0a2b011b88244175bdb0cabbc2283179 +size 2983914 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ccc6e4f05b1dd4152af1a680f0deb281f0397e28 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438bb6ccabda320799cfa6a9337c88a5caed95ed124b19f39ff44b6ae6faa93f +size 3532408 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..01dc14606e8d5050c7bcf8cc41435ab20fd7cbbd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b319068035f0e178a11e10a228db505bff084027497d0aab67218278d2ac9b3 +size 8161724 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7f72027fcb71ea777cf403551ff5ccbe0fed913e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ffdda927b904d7a111003eb78846e0266f5d6c70cc2ba5cdb66b4bbb681e5c5 +size 4627794 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..95251e5b1633b5ccd4b372d796af4c52062d6b96 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bdd0430f65d21bc876068cd7299dfcae0a1506a45368a85159146ead66b520d +size 2369370 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..215113df42991a4a0bfb53bcd8ddf8eeaa856218 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af0b280e97f1f8567441849ffe757c8f9cb48cb20828be41960b7ff2bb9884f +size 3208697 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2a1925cb7089d8567a387acd81e61fc295c9ed81 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c3444e80311b35365c7ac814aecaff6037125b151cea8eb0da1cbc7833bc31 +size 4039510 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4c212c9874f7241b69e88613e591463b6a1bbf06 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ecc8e56e3ce34f1e6fe887597f591ec34b5a8e64e12f4a363bc43c37f05f91 +size 4869588 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0f3f2075ded35135ca1f2ca4cd3f4de3c25c9a86 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74df6826d7392b4760e668102c2d7cbe2bb48064a6a24d015a8433fd53cae42 +size 5700044 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cc17eadb0c6e669af22e4422869737d61b2cd9f4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22c2d0db35512371a183cea5ee092727290a0c8ed987a047a950e2d3a14e0fc +size 6529379 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0bfde691bde6679ecf4e4498133ee28d2a950ee4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3a59fc49e1b7c8048a75cbb08e048f908793d291f7c00559b0187e75c84a85 +size 2343314 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f2df5fe663fb6a9466b5a3b0b5dab285003ad060 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01930e83b7ac37709966a83abd23dea9a3d715a52ca18594ba98f892c52b64ea +size 3155842 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fe11b2f8881b21cf1862f9eb5e67fd1710e36cfc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751e71dc90f42f38f52355ea01fdf1deb9fb5a8e7e66d49f38c88aba66862437 +size 3960654 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7effa5d18f77eb346ec6c07826cca5e69fc93c5f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5967ef633b0d32771cf09601209283e98ba54a33c9776b825a3122f234003e +size 4764375 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac963b458a91d89fd6e104090a37df129b165005 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1742351d5b2fafd580ca2351c89922b8076e765d22c0e6ff0a66bd6f7ebb5d8 +size 5568689 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..85dbb28f51d46129b3de40e60049d414c37fd26e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc2cfd4d2e64736e2d32454d165e988a47f12601dfab9b1f28cddf32116460c +size 6371630 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7e58a922852517a4e842e0f0a2783c19ae0ff2e0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70fb4f58659e9d56a82e0aef3a6f50237a6984ca0a15d2bb9d6c569e128751f9 +size 250583 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..478cd6c6658569b5b2fbee7b51c73bbf2a927eb9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae90ed6e58347ea6642e947fc27271537d3d362f3222e9b2a3f62a0021b597b +size 351384 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bd54105d95008bd3f504e64423916f3b1cf86f0f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19b6dfe7afb2456a8007d629ca4234ba60d646c4931d61800dcde594edfb3f07 +size 449673 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5212915014c550201db434f30032082e06e3fb07 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0ae7552c1d877dd3674841abdc6abba5b73aa4bbed5e5e8b243f40c2faf44e +size 553038 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2643ac99e47f98127bf3cb4c697639dca398e3b6 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a61d48a7b236b50e6d3eccc7379b761eb84295b1f1e49fcab1e4659a1e56bb +size 651651 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2fd1859d29d091f61f9ea6dabd6baeb9df8d0995 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_GPT-3-style_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36f18cb51705f38dacedc256074b68143d451311b239b90d174b5a2d84f65dba +size 747534 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d511aa36201e093bcce29e800c5b1f770caa7554 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:381dfb7992e61072753f7568b0357a7d431f5f9c4e8461298672dd7f56f32a44 +size 293154 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b53d29523f7871e98a14a662c847e2251afe52d5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933614fd70252775281c922989398bd97d3d18e5ebcb5f28d1bf98c2f67c4fde +size 415473 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ecbdd6b4c9f17789097830d0e51f7232867fb01b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a416c7e4080b3033ec7687a3d0d989d6a15adc85d5e786f59a963da4501fec +size 535372 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..987d0d6b823ab773c8a7cda51aab0b274413c18e --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:833001c474c1c9c10c3076f0f2a473a2a6e6d14bf1c471b676c04b0ff656982d +size 660368 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c689e3d8517764cda02f448f19ee1bb3a547cadc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a98772d4ebc00699892e6545be4229043b0373a8254a239307fa5cc1c6a5c51 +size 780585 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e024161ef3864a2472f06d550a309928f195c568 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19690e7c512fb27f2c56c0c22cbc174f157da295dc18841a363af4f93174c561 +size 898086 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9ca90c58841d88f72f566ea12f20d2254c0e54b9 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c77cea234d79305438970c8053c7fc09759e7de8528e9a2b5b8c2e0a4ae8fe +size 258517 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dd7e4089ee68c3a8026d987176a74632c3277a7d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c69349f34a0ec953965ebfeb45b1433f427312de5fed03432eb60e0cb6abec +size 363054 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f476f50aa530f7d93eb9e4c18482ab525f79672f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88eb21155579770596726ae810a7f930722ad245b55bc562da4f138cf67a7e9a +size 465288 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5c2a81ed3011eb3112b7622a20379f60a6f80364 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d41336d24b252cbfdb808fdb27fabe9ac9f1a1a914149d3f14abc4d9debf6c2 +size 572554 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a3f8e74601063f6f1c7c959e6c14cace954a0ef --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d37a910fe1bceec20b26f9ad13c20f6d6a541f49179dba2e6de5788c78ac522 +size 675034 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1b2664a3de686440aa3900c97c321f6a1185b0c7 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6f1030b7b7c85681e20ba42f44dd32b33614a1f70d6dace6bfa0c50c89ff82e +size 774822 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2863aaa467863767a4a9ab5c15400266a46e2ccf --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75100a8e035fc4bdb442e2b952e5700b9145124f9cb0c344148bc435a7c7ccb0 +size 261297 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..98c16d5a798e325b828af5aaa945e28b03b29648 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f689d0a1e816bff4deda25f91f482de9ed496f983e34bfc09d6ce8c7dec977 +size 367780 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f758708d757a8ae08b20f1533cff25d7894f09e5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c80119210a875e1e7fa118ec0fa6727ab02f9ec428f576c9f46fddb8996770 +size 471935 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9077f0c9fbfd0781d30aac869586b42436c9a480 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2ef159e5eccd585465c0fed4fa951d3b1ae5d3c84f29a32c48f0b7d76193d7 +size 581136 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..319452741063dbfa5bf613f88f841796df9b5e4f --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9333d83019b1cf28895dd5b416cbd827c4f25b68a7ad23731fae217340744919 +size 685549 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..351d79322f455526724278bdd41f90ed9ef1e3bb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_guaranteed-true_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:255011ab642c7bb1487b207a80dd21da4c03ee4fe0251930d479b0d60d24a8d8 +size 787271 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..95b7d93fa4905bdaa8611db131958929264f6ce5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f602aa8da2682eae0a745b8b6db898c01c5fe99a96b1a1bd843659e48030f7c +size 262407 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5fe4389a55462c8bedf610656cbb5784d716e8b1 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:910920db66b2f6175ef022dcb0a7279a322ae696eb9fe9e59976c26aad423714 +size 369791 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..409642a5d14294b301f11b9b66aec458ab174026 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8271c0c11a32dcc03a46e51b6023d20c69c26b2f19f1b2583fae7789ab6186 +size 474710 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..53c0a3a51ff6b667b5e5e7184604409776060d9d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58829eb4b8f9978046c2feecbb555f24bfe8380b7e5185e87c7faba13eb69ef2 +size 584756 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9339ccaac3ee04b3463c6c1d2aedf0ede5d652cb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96fe611f121cc7a7d945e50459391aecccd54a83536f668a2138ccbd66072313 +size 690005 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f677911a9cd9924306aaa6c81f2a0659e7522034 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_superglue_rte_should-assume_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71d9ce3ea40e810d7a981d438cce340131dc0fc469960635ab1e11a40b5f81e +size 792556 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..45624be50126875001073d93f6affd21a6b205c4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663eef91437191f843b124c50b8455baf96e7d842033ed809b20bf4b7e38e5c2 +size 1039123 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..45419443ea1a371ae79c0c3cac7a187835087381 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725a95ac810ad6c484ccb5303b7856621faad0c202b3fd1018d32a9ad95190c0 +size 1300039 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8fe6c20e32d74fc12e2f95b3b94cb2db2b2a70d5 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed0a92ccbae8f36f71fd5bbd7f7146cf3f246125ebb8c3bb7bff428e250b28f +size 1561151 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ae3706042ea8bd9e71d86b1752f789b61b316b40 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15569ab4b7b90d729cf83cf2701dd36d56fd6a6f657f7b74167c44d045416197 +size 1822571 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f98180b7815b230384218a7206511aff3bd9e928 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2757ec890ea86999abc02c9a61383f652480842ab0c13399fab2b6f557d2c27b +size 2082850 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1f656b82faf67eccb4029dd2787e97f5403facd4 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_Replace_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f1f39ec1ad4d9c2a22ac02dc0d8151edb9889c7b71a774ebae56d7b8b3aebb +size 2343602 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8b78b4de5c67845f5992c76705e25e5b913fa207 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2fbbe63377a155d4a76680136bc82c48c517daddcc3296bb1ea3d5486959f0 +size 948112 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c94a80a68a68de358a1e37b9e4a16cf75ca56edc --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd6ab6a5d930ce36bc9a3808df59d05eb9d79eeecab0039faa43142869e6099 +size 1180707 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fdc2555d9c363dab4789f5589e4113a1b158d59b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad8604c233bbe91f3d2668215dabc071ff63c6946dd6eb563df187f7e672682e +size 1413260 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e11d93414c7d98a9417740f87698c284b1c69530 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3edc337a23c12de974d83277667fa5c1cc6117334e0a33717a2cc83c6a26d4 +size 1646093 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..537c8baa067923239b0f050c57e221e36e278920 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea52542cd6405d5afee03dbfbb9907ddaf4f51bdde77996e566a2892bf71c242 +size 1877991 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..649af5c8d5f562d73a6f71e06a94f01dc0c3eb50 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_True-or-False_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc37b28d02bea70bb7a550110344721636377d974214488b3fb256fe559bc1fb +size 2110070 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fe5fe1dab426b75835e6a1a8160fd53774aa2af0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67c5aaecbee363b63a280da2397b9502cd7c32114213a31c5b3558d7f90067d +size 1009880 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c372e8e09933b77e67c6d54d9a46acc6936f6c04 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7792908ac666f4522e44a464d5926dcd4bc70a8ad111a4652ef3a7de3617f60e +size 1243015 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..10db261860db33a224c423127abf56cb573ceff0 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27ee4364a7c79034ac3926bb70c858976a1d127f6bd8c9127b8e13002b7c9ab +size 2952438 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7246ebf8189b8aa5bc95a7988a207894f979f2bb --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c7757e59daf6422c2010005f075a3e46fea0f9e2d15493d226552a49c4d541 +size 1709857 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..486685294dc9d291fb8d49490fcd047131de574b --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265dfb40ef1944342299deb26d02ab51efcb0533be29e3bd0deba3936512e822 +size 1942191 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c234d215d60f2f716ac4321f2797eef398cacc39 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95be17ecba7d4474d37e101e3599383dd5b4e6b97aa40d9610f4193a6d89243 +size 2175033 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..29b90b393c036ce741df262b8f9e58646367a78d --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a18b84287746fade2cfeebc0192d4d21b3704efbc5e14ecfd661a5484a0af50 +size 969267 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7ad06795186265e007469e5a624e92bd0d1ebffe --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b3649a154bd8ae056c3876d3c506e48dc94d1ffe27d79aab8fd4eadc09d6f3 +size 1204889 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c9fb36b82f9e951f6b476afb7fbfea4cafce7b86 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4be3321b731a4759fbf28c9d6b4923d9f61ae9fc3b09a8f829ba45c43e343d +size 1440752 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..04fe269017175aa7c63880419e782bf487a67bea --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9f466b8290f4f0d1d45b52a27c0ccc037037d06a545a9a7790cbca2c6e5a8a +size 1676899 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8d0bf45cc9a4a24358740418144ae50debc07661 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c985a68c5cbb619a8213b8ba817a9aa8a179962cfc5c08e7218489da078275 +size 1911920 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac28e656416694657da86fde4ea658ce9c066ddd --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_stand-for_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815c1ac3ac778422443a45108a1319392784b031fcde396c7d6c7e556ea99952 +size 2147263 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_0.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_0.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..196fb0b12308ac26c2461fe1b1198f1a57f555e3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_0.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2f7cd00f28b8c56330fd201ba202d8d8f06c71017665c4875f36e5ed11c83d +size 1016369 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_1.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_1.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cf75e442ab294d2d8c67702a802bd767e7229c21 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_1.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58251b36e87cf1cca8de8d9a93f949b95b05708598de31628fcc0c90f996b13e +size 1256984 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_2.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_2.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac463c264d95281cc1bfc46d3cca3b84875d9a81 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_2.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41d459dddff63b22d2b4c02c0423d149fb62395b3db5311586ecee019097e68 +size 1497823 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_3.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_3.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..486a09476c2b8919774c62947eea0bf0bceb528a --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_3.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21c482d8f254dece8fb549479baaba915e17999aa3b06410207a97c6ef486f5 +size 1739034 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_4.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_4.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..211e7f84e91f17eee33e32bb04401b8d4a9faae3 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_4.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4b067504644b15377f8acb2e47496920f9cc236c850c12dd1ae4090b14fb2b +size 3958082 diff --git a/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_5.jsonl b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3b67f9df68bcd09bdb8232eea953e4d051377e32 --- /dev/null +++ b/421m3b93b9/eval/examples.lm1-421m-3b9_winogrande_underscore-refer-to_5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1800a2c4ff0a414a8af84e4cc2367a5a6cf7c48ea9a6184298306ce96e9d854 +size 2219520 diff --git a/421m3b93b9/eval/merged.csv b/421m3b93b9/eval/merged.csv new file mode 100644 index 0000000000000000000000000000000000000000..a839a2fc427ab675a464390e48fb141b933ff1cc --- /dev/null +++ b/421m3b93b9/eval/merged.csv @@ -0,0 +1,587 @@ +dataset,fewshots,prompt,metric,value +anli_r1,0,GPT-3 style,acc,0.329 +anli_r1,0,MNLI crowdsource,acc,0.331 +anli_r1,0,can we infer,acc,0.336 +anli_r1,0,guaranteed/possible/impossible,acc,0.324 +anli_r1,0,justified in saying,acc,0.333 +anli_r1,0,median,accuracy,0.331 +anli_r1,1,GPT-3 style,acc,0.334 +anli_r1,1,MNLI crowdsource,acc,0.333 +anli_r1,1,can we infer,acc,0.331 +anli_r1,1,guaranteed/possible/impossible,acc,0.333 +anli_r1,1,justified in saying,acc,0.332 +anli_r1,1,median,accuracy,0.333 +anli_r1,2,GPT-3 style,acc,0.363 +anli_r1,2,MNLI crowdsource,acc,0.339 +anli_r1,2,can we infer,acc,0.353 +anli_r1,2,guaranteed/possible/impossible,acc,0.348 +anli_r1,2,justified in saying,acc,0.353 +anli_r1,2,median,accuracy,0.353 +anli_r1,3,GPT-3 style,acc,0.355 +anli_r1,3,MNLI crowdsource,acc,0.329 +anli_r1,3,can we infer,acc,0.35 +anli_r1,3,guaranteed/possible/impossible,acc,0.35 +anli_r1,3,justified in saying,acc,0.346 +anli_r1,3,median,accuracy,0.35 +anli_r1,4,GPT-3 style,acc,0.348 +anli_r1,4,MNLI crowdsource,acc,0.327 +anli_r1,4,can we infer,acc,0.335 +anli_r1,4,guaranteed/possible/impossible,acc,0.325 +anli_r1,4,justified in saying,acc,0.345 +anli_r1,4,median,accuracy,0.335 +anli_r1,5,GPT-3 style,acc,0.352 +anli_r1,5,MNLI crowdsource,acc,0.308 +anli_r1,5,can we infer,acc,0.342 +anli_r1,5,guaranteed/possible/impossible,acc,0.328 +anli_r1,5,justified in saying,acc,0.344 +anli_r1,5,median,accuracy,0.342 +anli_r1,5,average,multiple,0.3406666666666667 +anli_r2,0,GPT-3 style,acc,0.32 +anli_r2,0,MNLI crowdsource,acc,0.339 +anli_r2,0,can we infer,acc,0.33 +anli_r2,0,guaranteed/possible/impossible,acc,0.334 +anli_r2,0,justified in saying,acc,0.333 +anli_r2,0,median,accuracy,0.333 +anli_r2,1,GPT-3 style,acc,0.321 +anli_r2,1,MNLI crowdsource,acc,0.315 +anli_r2,1,can we infer,acc,0.325 +anli_r2,1,guaranteed/possible/impossible,acc,0.315 +anli_r2,1,justified in saying,acc,0.324 +anli_r2,1,median,accuracy,0.321 +anli_r2,2,GPT-3 style,acc,0.33 +anli_r2,2,MNLI crowdsource,acc,0.327 +anli_r2,2,can we infer,acc,0.326 +anli_r2,2,guaranteed/possible/impossible,acc,0.321 +anli_r2,2,justified in saying,acc,0.328 +anli_r2,2,median,accuracy,0.327 +anli_r2,3,GPT-3 style,acc,0.321 +anli_r2,3,MNLI crowdsource,acc,0.329 +anli_r2,3,can we infer,acc,0.312 +anli_r2,3,guaranteed/possible/impossible,acc,0.296 +anli_r2,3,justified in saying,acc,0.318 +anli_r2,3,median,accuracy,0.318 +anli_r2,4,GPT-3 style,acc,0.327 +anli_r2,4,MNLI crowdsource,acc,0.305 +anli_r2,4,can we infer,acc,0.316 +anli_r2,4,guaranteed/possible/impossible,acc,0.316 +anli_r2,4,justified in saying,acc,0.314 +anli_r2,4,median,accuracy,0.316 +anli_r2,5,GPT-3 style,acc,0.337 +anli_r2,5,MNLI crowdsource,acc,0.313 +anli_r2,5,can we infer,acc,0.326 +anli_r2,5,guaranteed/possible/impossible,acc,0.325 +anli_r2,5,justified in saying,acc,0.329 +anli_r2,5,median,accuracy,0.326 +anli_r2,5,average,multiple,0.3235 +anli_r3,0,GPT-3 style,acc,0.30416666666666664 +anli_r3,0,MNLI crowdsource,acc,0.3358333333333333 +anli_r3,0,can we infer,acc,0.3233333333333333 +anli_r3,0,guaranteed/possible/impossible,acc,0.32916666666666666 +anli_r3,0,justified in saying,acc,0.33166666666666667 +anli_r3,0,median,accuracy,0.32916666666666666 +anli_r3,1,GPT-3 style,acc,0.3433333333333333 +anli_r3,1,MNLI crowdsource,acc,0.33666666666666667 +anli_r3,1,can we infer,acc,0.345 +anli_r3,1,guaranteed/possible/impossible,acc,0.33666666666666667 +anli_r3,1,justified in saying,acc,0.355 +anli_r3,1,median,accuracy,0.3433333333333333 +anli_r3,2,GPT-3 style,acc,0.335 +anli_r3,2,MNLI crowdsource,acc,0.30833333333333335 +anli_r3,2,can we infer,acc,0.3275 +anli_r3,2,guaranteed/possible/impossible,acc,0.31333333333333335 +anli_r3,2,justified in saying,acc,0.33166666666666667 +anli_r3,2,median,accuracy,0.3275 +anli_r3,3,GPT-3 style,acc,0.3541666666666667 +anli_r3,3,MNLI crowdsource,acc,0.3308333333333333 +anli_r3,3,can we infer,acc,0.3433333333333333 +anli_r3,3,guaranteed/possible/impossible,acc,0.32 +anli_r3,3,justified in saying,acc,0.345 +anli_r3,3,median,accuracy,0.3433333333333333 +anli_r3,4,GPT-3 style,acc,0.34833333333333333 +anli_r3,4,MNLI crowdsource,acc,0.32916666666666666 +anli_r3,4,can we infer,acc,0.3466666666666667 +anli_r3,4,guaranteed/possible/impossible,acc,0.3175 +anli_r3,4,justified in saying,acc,0.3408333333333333 +anli_r3,4,median,accuracy,0.3408333333333333 +anli_r3,5,GPT-3 style,acc,0.32916666666666666 +anli_r3,5,MNLI crowdsource,acc,0.29833333333333334 +anli_r3,5,can we infer,acc,0.3308333333333333 +anli_r3,5,guaranteed/possible/impossible,acc,0.31 +anli_r3,5,justified in saying,acc,0.32666666666666666 +anli_r3,5,median,accuracy,0.32666666666666666 +anli_r3,5,average,multiple,0.3351388888888889 +arc_easy,0,heres_a_problem,acc,0.2175767918088737 +arc_easy,0,i_am_hesitating,acc,0.2158703071672355 +arc_easy,0,multiple_choice,acc,0.29124579124579125 +arc_easy,0,pick_the_most_correct_option,acc,0.22013651877133106 +arc_easy,0,qa_options,acc,0.20648464163822525 +arc_easy,0,median,accuracy,0.2175767918088737 +arc_easy,1,heres_a_problem,acc,0.23779461279461278 +arc_easy,1,i_am_hesitating,acc,0.2235494880546075 +arc_easy,1,multiple_choice,acc,0.22866894197952217 +arc_easy,1,pick_the_most_correct_option,acc,0.2398989898989899 +arc_easy,1,qa_options,acc,0.29503367003367004 +arc_easy,1,median,accuracy,0.23779461279461278 +arc_easy,2,heres_a_problem,acc,0.23208191126279865 +arc_easy,2,i_am_hesitating,acc,0.2167235494880546 +arc_easy,2,multiple_choice,acc,0.2895622895622896 +arc_easy,2,pick_the_most_correct_option,acc,0.2596801346801347 +arc_easy,2,qa_options,acc,0.2908249158249158 +arc_easy,2,median,accuracy,0.2596801346801347 +arc_easy,3,heres_a_problem,acc,0.25841750841750843 +arc_easy,3,i_am_hesitating,acc,0.2803030303030303 +arc_easy,3,multiple_choice,acc,0.27735690235690236 +arc_easy,3,pick_the_most_correct_option,acc,0.2537878787878788 +arc_easy,3,qa_options,acc,0.2824074074074074 +arc_easy,3,median,accuracy,0.27735690235690236 +arc_easy,4,heres_a_problem,acc,0.24146757679180889 +arc_easy,4,i_am_hesitating,acc,0.23037542662116042 +arc_easy,4,multiple_choice,acc,0.2781986531986532 +arc_easy,4,pick_the_most_correct_option,acc,0.2542087542087542 +arc_easy,4,qa_options,acc,0.2150170648464164 +arc_easy,4,median,accuracy,0.24146757679180889 +arc_easy,5,heres_a_problem,acc,0.25715488215488214 +arc_easy,5,i_am_hesitating,acc,0.22610921501706485 +arc_easy,5,multiple_choice,acc,0.2735690235690236 +arc_easy,5,pick_the_most_correct_option,acc,0.22866894197952217 +arc_easy,5,qa_options,acc,0.22184300341296928 +arc_easy,5,median,accuracy,0.22866894197952217 +arc_easy,5,average,multiple,0.24375749340197578 +boolq,0,GPT-3 Style,acc,0.48933333333333334 +boolq,0,after_reading,acc,0.6196666666666667 +boolq,0,exercise,acc,0.6203333333333333 +boolq,0,valid_binary,acc,0.5126666666666667 +boolq,0,yes_no_question,acc,0.6236666666666667 +boolq,0,median,accuracy,0.6196666666666667 +boolq,1,GPT-3 Style,acc,0.5403333333333333 +boolq,1,after_reading,acc,0.5406666666666666 +boolq,1,exercise,acc,0.5406666666666666 +boolq,1,valid_binary,acc,0.5403333333333333 +boolq,1,yes_no_question,acc,0.6153333333333333 +boolq,1,median,accuracy,0.5406666666666666 +boolq,2,GPT-3 Style,acc,0.5376666666666666 +boolq,2,after_reading,acc,0.5213333333333333 +boolq,2,exercise,acc,0.56 +boolq,2,valid_binary,acc,0.556 +boolq,2,yes_no_question,acc,0.6126666666666667 +boolq,2,median,accuracy,0.556 +boolq,3,GPT-3 Style,acc,0.561 +boolq,3,after_reading,acc,0.55 +boolq,3,exercise,acc,0.5726666666666667 +boolq,3,valid_binary,acc,0.5573333333333333 +boolq,3,yes_no_question,acc,0.613 +boolq,3,median,accuracy,0.561 +boolq,4,GPT-3 Style,acc,0.5606666666666666 +boolq,4,after_reading,acc,0.5443333333333333 +boolq,4,exercise,acc,0.581 +boolq,4,valid_binary,acc,0.5676666666666667 +boolq,4,yes_no_question,acc,0.6226666666666667 +boolq,4,median,accuracy,0.5676666666666667 +boolq,5,GPT-3 Style,acc,0.564 +boolq,5,after_reading,acc,0.5556666666666666 +boolq,5,exercise,acc,0.5846666666666667 +boolq,5,valid_binary,acc,0.5763333333333334 +boolq,5,yes_no_question,acc,0.6216666666666667 +boolq,5,median,accuracy,0.5763333333333334 +boolq,5,average,multiple,0.5702222222222222 +cb,0,GPT-3 style,acc,0.32142857142857145 +cb,0,MNLI crowdsource,acc,0.4107142857142857 +cb,0,can we infer,acc,0.42857142857142855 +cb,0,guaranteed/possible/impossible,acc,0.39285714285714285 +cb,0,justified in saying,acc,0.4107142857142857 +cb,0,median,accuracy,0.4107142857142857 +cb,1,GPT-3 style,acc,0.35714285714285715 +cb,1,MNLI crowdsource,acc,0.39285714285714285 +cb,1,can we infer,acc,0.4642857142857143 +cb,1,guaranteed/possible/impossible,acc,0.39285714285714285 +cb,1,justified in saying,acc,0.4642857142857143 +cb,1,median,accuracy,0.39285714285714285 +cb,2,GPT-3 style,acc,0.4107142857142857 +cb,2,MNLI crowdsource,acc,0.42857142857142855 +cb,2,can we infer,acc,0.4107142857142857 +cb,2,guaranteed/possible/impossible,acc,0.44642857142857145 +cb,2,justified in saying,acc,0.4107142857142857 +cb,2,median,accuracy,0.4107142857142857 +cb,3,GPT-3 style,acc,0.39285714285714285 +cb,3,MNLI crowdsource,acc,0.44642857142857145 +cb,3,can we infer,acc,0.4642857142857143 +cb,3,guaranteed/possible/impossible,acc,0.4107142857142857 +cb,3,justified in saying,acc,0.44642857142857145 +cb,3,median,accuracy,0.44642857142857145 +cb,4,GPT-3 style,acc,0.375 +cb,4,MNLI crowdsource,acc,0.39285714285714285 +cb,4,can we infer,acc,0.42857142857142855 +cb,4,guaranteed/possible/impossible,acc,0.5178571428571429 +cb,4,justified in saying,acc,0.42857142857142855 +cb,4,median,accuracy,0.42857142857142855 +cb,5,GPT-3 style,acc,0.39285714285714285 +cb,5,MNLI crowdsource,acc,0.35714285714285715 +cb,5,can we infer,acc,0.4107142857142857 +cb,5,guaranteed/possible/impossible,acc,0.5 +cb,5,justified in saying,acc,0.39285714285714285 +cb,5,median,accuracy,0.39285714285714285 +cb,5,average,multiple,0.41369047619047616 +copa,0,best_option,acc,0.58 +copa,0,cause_effect,acc,0.59 +copa,0,choose,acc,0.58 +copa,0,i_am_hesitating,acc,0.56 +copa,0,plausible_alternatives,acc,0.56 +copa,0,median,accuracy,0.58 +copa,1,best_option,acc,0.53 +copa,1,cause_effect,acc,0.54 +copa,1,choose,acc,0.55 +copa,1,i_am_hesitating,acc,0.48 +copa,1,plausible_alternatives,acc,0.52 +copa,1,median,accuracy,0.53 +copa,2,best_option,acc,0.55 +copa,2,cause_effect,acc,0.56 +copa,2,choose,acc,0.55 +copa,2,i_am_hesitating,acc,0.52 +copa,2,plausible_alternatives,acc,0.53 +copa,2,median,accuracy,0.55 +copa,3,best_option,acc,0.55 +copa,3,cause_effect,acc,0.54 +copa,3,choose,acc,0.53 +copa,3,i_am_hesitating,acc,0.49 +copa,3,plausible_alternatives,acc,0.52 +copa,3,median,accuracy,0.53 +copa,4,best_option,acc,0.51 +copa,4,cause_effect,acc,0.55 +copa,4,choose,acc,0.54 +copa,4,i_am_hesitating,acc,0.47 +copa,4,plausible_alternatives,acc,0.51 +copa,4,median,accuracy,0.51 +copa,5,best_option,acc,0.55 +copa,5,cause_effect,acc,0.54 +copa,5,choose,acc,0.53 +copa,5,i_am_hesitating,acc,0.5 +copa,5,plausible_alternatives,acc,0.51 +copa,5,median,accuracy,0.53 +copa,5,average,multiple,0.5383333333333333 +e2e_nlg_cleaned,0,coherent_text,rouge2_fmeasure,0.0413168613300981 +e2e_nlg_cleaned,0,create_text_for_me,rouge2_fmeasure,0.13691922129643072 +e2e_nlg_cleaned,0,generate_gramatically_correct_text,rouge2_fmeasure,0.10374767270154109 +e2e_nlg_cleaned,0,generate_text_restaurant,rouge2_fmeasure,0.010123335458248412 +e2e_nlg_cleaned,0,text,rouge2_fmeasure,0.07857762779721571 +e2e_nlg_cleaned,0,median,rouge2_fmeasure,0.07857762779721571 +e2e_nlg_cleaned,1,coherent_text,rouge2_fmeasure,0.09705173957954942 +e2e_nlg_cleaned,1,create_text_for_me,rouge2_fmeasure,0.09291021571347792 +e2e_nlg_cleaned,1,generate_gramatically_correct_text,rouge2_fmeasure,0.11246784846792322 +e2e_nlg_cleaned,1,generate_text_restaurant,rouge2_fmeasure,0.10817189459012165 +e2e_nlg_cleaned,1,text,rouge2_fmeasure,0.11238103667987336 +e2e_nlg_cleaned,1,median,rouge2_fmeasure,0.10817189459012165 +e2e_nlg_cleaned,2,coherent_text,rouge2_fmeasure,0.12480576931000954 +e2e_nlg_cleaned,2,create_text_for_me,rouge2_fmeasure,0.11731827518171299 +e2e_nlg_cleaned,2,generate_gramatically_correct_text,rouge2_fmeasure,0.12416901504237551 +e2e_nlg_cleaned,2,generate_text_restaurant,rouge2_fmeasure,0.12966947477583363 +e2e_nlg_cleaned,2,text,rouge2_fmeasure,0.13240317910861094 +e2e_nlg_cleaned,2,median,rouge2_fmeasure,0.12480576931000954 +e2e_nlg_cleaned,3,coherent_text,rouge2_fmeasure,0.13345925813528606 +e2e_nlg_cleaned,3,create_text_for_me,rouge2_fmeasure,0.12734114879849334 +e2e_nlg_cleaned,3,generate_gramatically_correct_text,rouge2_fmeasure,0.1327243773594466 +e2e_nlg_cleaned,3,generate_text_restaurant,rouge2_fmeasure,0.13691320451323 +e2e_nlg_cleaned,3,text,rouge2_fmeasure,0.1375143860984762 +e2e_nlg_cleaned,3,median,rouge2_fmeasure,0.13345925813528606 +e2e_nlg_cleaned,4,coherent_text,rouge2_fmeasure,0.139368667490815 +e2e_nlg_cleaned,4,create_text_for_me,rouge2_fmeasure,0.1322742849122928 +e2e_nlg_cleaned,4,generate_gramatically_correct_text,rouge2_fmeasure,0.13722355902976058 +e2e_nlg_cleaned,4,generate_text_restaurant,rouge2_fmeasure,0.13896898011991943 +e2e_nlg_cleaned,4,text,rouge2_fmeasure,0.14197862193928545 +e2e_nlg_cleaned,4,median,rouge2_fmeasure,0.13896898011991943 +e2e_nlg_cleaned,5,coherent_text,rouge2_fmeasure,0.1433273164318412 +e2e_nlg_cleaned,5,create_text_for_me,rouge2_fmeasure,0.13899954079181534 +e2e_nlg_cleaned,5,generate_gramatically_correct_text,rouge2_fmeasure,0.14239753185765971 +e2e_nlg_cleaned,5,generate_text_restaurant,rouge2_fmeasure,0.14603196173656227 +e2e_nlg_cleaned,5,text,rouge2_fmeasure,0.14479391497677302 +e2e_nlg_cleaned,5,median,rouge2_fmeasure,0.1433273164318412 +e2e_nlg_cleaned,5,average,multiple,0.12121847439739894 +gem_xsum,0,DOC_boils_down_to_simple_idea_that,rouge2_fmeasure,0.016871170959750856 +gem_xsum,0,DOC_tldr,rouge2_fmeasure,0.019716305531943378 +gem_xsum,0,article_DOC_summary,rouge2_fmeasure,0.02780910006627101 +gem_xsum,0,summarize_DOC,rouge2_fmeasure,0.02216490573223825 +gem_xsum,0,summarize_this_DOC_summary,rouge2_fmeasure,0.02550920276281168 +gem_xsum,0,median,rouge2_fmeasure,0.02216490573223825 +gem_xsum,1,DOC_boils_down_to_simple_idea_that,rouge2_fmeasure,0.015898317357067135 +gem_xsum,1,DOC_tldr,rouge2_fmeasure,0.012104885502617603 +gem_xsum,1,article_DOC_summary,rouge2_fmeasure,0.024161160413064688 +gem_xsum,1,summarize_DOC,rouge2_fmeasure,0.024050432775105567 +gem_xsum,1,summarize_this_DOC_summary,rouge2_fmeasure,0.0254681124378878 +gem_xsum,1,median,rouge2_fmeasure,0.024050432775105567 +gem_xsum,2,DOC_boils_down_to_simple_idea_that,rouge2_fmeasure,0.0174749223761466 +gem_xsum,2,DOC_tldr,rouge2_fmeasure,0.016540998688253494 +gem_xsum,2,article_DOC_summary,rouge2_fmeasure,0.021955967558594934 +gem_xsum,2,summarize_DOC,rouge2_fmeasure,0.021850132907452764 +gem_xsum,2,summarize_this_DOC_summary,rouge2_fmeasure,0.02344635398091455 +gem_xsum,2,median,rouge2_fmeasure,0.021850132907452764 +gem_xsum,3,DOC_boils_down_to_simple_idea_that,rouge2_fmeasure,0.01773853594640338 +gem_xsum,3,DOC_tldr,rouge2_fmeasure,0.01889574180325777 +gem_xsum,3,article_DOC_summary,rouge2_fmeasure,0.020853724585447975 +gem_xsum,3,summarize_DOC,rouge2_fmeasure,0.020384730084258812 +gem_xsum,3,summarize_this_DOC_summary,rouge2_fmeasure,0.021683379341115812 +gem_xsum,3,median,rouge2_fmeasure,0.020384730084258812 +gem_xsum,4,DOC_boils_down_to_simple_idea_that,rouge2_fmeasure,0.004783264838725394 +gem_xsum,4,DOC_tldr,rouge2_fmeasure,0.006640579605150196 +gem_xsum,4,article_DOC_summary,rouge2_fmeasure,0.006231843463345877 +gem_xsum,4,summarize_DOC,rouge2_fmeasure,0.007018029042731219 +gem_xsum,4,summarize_this_DOC_summary,rouge2_fmeasure,0.006054078203169595 +gem_xsum,4,median,rouge2_fmeasure,0.006231843463345877 +gem_xsum,5,DOC_boils_down_to_simple_idea_that,rouge2_fmeasure,0.0 +gem_xsum,5,DOC_tldr,rouge2_fmeasure,0.0002397463551736582 +gem_xsum,5,article_DOC_summary,rouge2_fmeasure,0.00020969228861543636 +gem_xsum,5,summarize_DOC,rouge2_fmeasure,0.00027004452530749476 +gem_xsum,5,summarize_this_DOC_summary,rouge2_fmeasure,5.360205831903945e-05 +gem_xsum,5,median,rouge2_fmeasure,0.00020969228861543636 +gem_xsum,5,average,multiple,0.015815289541836117 +piqa,0,Correct the solution,rouge2_fmeasure,0.09519041983155013 +piqa,0,choose the most appropriate solution,acc,0.49075081610446136 +piqa,0,no prompt needed,rouge2_fmeasure,0.004256247232539841 +piqa,0,pick_correct_choice_index,acc,0.49510337323177367 +piqa,0,what_is_the_correct_ending,acc,0.5233949945593036 +piqa,0,median,accuracy,0.49510337323177367 +piqa,1,Correct the solution,rouge2_fmeasure,0.1734691615853129 +piqa,1,choose the most appropriate solution,acc,0.5021762785636561 +piqa,1,no prompt needed,rouge2_fmeasure,0.007609013308850757 +piqa,1,pick_correct_choice_index,acc,0.5038084874863983 +piqa,1,what_is_the_correct_ending,acc,0.5212187159956474 +piqa,1,median,accuracy,0.5038084874863983 +piqa,2,Correct the solution,rouge2_fmeasure,0.25734856308354354 +piqa,2,choose the most appropriate solution,acc,0.5043525571273123 +piqa,2,no prompt needed,rouge2_fmeasure,0.006554418985992436 +piqa,2,pick_correct_choice_index,acc,0.4956474428726877 +piqa,2,what_is_the_correct_ending,acc,0.5255712731229597 +piqa,2,median,accuracy,0.5043525571273123 +piqa,3,Correct the solution,rouge2_fmeasure,0.30169097752148116 +piqa,3,choose the most appropriate solution,acc,0.5016322089227421 +piqa,3,no prompt needed,rouge2_fmeasure,0.006348389170194352 +piqa,3,pick_correct_choice_index,acc,0.5250272034820457 +piqa,3,what_is_the_correct_ending,acc,0.5206746463547334 +piqa,3,median,accuracy,0.5206746463547334 +piqa,4,Correct the solution,rouge2_fmeasure,0.32589784419427137 +piqa,4,choose the most appropriate solution,acc,0.5048966267682263 +piqa,4,no prompt needed,rouge2_fmeasure,0.0074306129720465705 +piqa,4,pick_correct_choice_index,acc,0.5239390642002176 +piqa,4,what_is_the_correct_ending,acc,0.5195865070729053 +piqa,4,median,accuracy,0.5195865070729053 +piqa,5,Correct the solution,rouge2_fmeasure,0.33520179328257893 +piqa,5,choose the most appropriate solution,acc,0.514145810663765 +piqa,5,no prompt needed,rouge2_fmeasure,0.008657019208894664 +piqa,5,pick_correct_choice_index,acc,0.5076169749727966 +piqa,5,what_is_the_correct_ending,acc,0.5125136017410229 +piqa,5,median,accuracy,0.5125136017410229 +piqa,5,average,multiple,0.5093398621690243 +sciq,0,Direct Question,acc,0.663 +sciq,0,Direct Question (Closed Book),acc,0.365 +sciq,0,Multiple Choice,acc,0.482 +sciq,0,Multiple Choice (Closed Book),acc,0.372 +sciq,0,Multiple Choice Question First,acc,0.516 +sciq,0,median,accuracy,0.482 +sciq,1,Direct Question,acc,0.715 +sciq,1,Direct Question (Closed Book),acc,0.393 +sciq,1,Multiple Choice,acc,0.335 +sciq,1,Multiple Choice (Closed Book),acc,0.32 +sciq,1,Multiple Choice Question First,acc,0.395 +sciq,1,median,accuracy,0.393 +sciq,2,Direct Question,acc,0.71 +sciq,2,Direct Question (Closed Book),acc,0.386 +sciq,2,Multiple Choice,acc,0.28 +sciq,2,Multiple Choice (Closed Book),acc,0.276 +sciq,2,Multiple Choice Question First,acc,0.323 +sciq,2,median,accuracy,0.323 +sciq,3,Direct Question,acc,0.722 +sciq,3,Direct Question (Closed Book),acc,0.383 +sciq,3,Multiple Choice,acc,0.28 +sciq,3,Multiple Choice (Closed Book),acc,0.3 +sciq,3,Multiple Choice Question First,acc,0.319 +sciq,3,median,accuracy,0.319 +sciq,4,Direct Question,acc,0.724 +sciq,4,Direct Question (Closed Book),acc,0.393 +sciq,4,Multiple Choice,acc,0.308 +sciq,4,Multiple Choice (Closed Book),acc,0.306 +sciq,4,Multiple Choice Question First,acc,0.322 +sciq,4,median,accuracy,0.322 +sciq,5,Direct Question,acc,0.728 +sciq,5,Direct Question (Closed Book),acc,0.384 +sciq,5,Multiple Choice,acc,0.289 +sciq,5,Multiple Choice (Closed Book),acc,0.298 +sciq,5,Multiple Choice Question First,acc,0.313 +sciq,5,median,accuracy,0.313 +sciq,5,average,multiple,0.3586666666666667 +story_cloze_2016,0,Answer Given options,acc,0.48583645109567075 +story_cloze_2016,0,Choose Story Ending,acc,0.5066809192944949 +story_cloze_2016,0,Novel Correct Ending,acc,0.47728487439871725 +story_cloze_2016,0,Story Continuation and Options,acc,0.49812934259754144 +story_cloze_2016,0,median,accuracy,0.4919828968466061 +story_cloze_2016,1,Answer Given options,acc,0.47835382148583644 +story_cloze_2016,1,Choose Story Ending,acc,0.47835382148583644 +story_cloze_2016,1,Novel Correct Ending,acc,0.47247461250668094 +story_cloze_2016,1,Story Continuation and Options,acc,0.4794227685729556 +story_cloze_2016,1,median,accuracy,0.47835382148583644 +story_cloze_2016,2,Answer Given options,acc,0.4767504008551577 +story_cloze_2016,2,Choose Story Ending,acc,0.4794227685729556 +story_cloze_2016,2,Novel Correct Ending,acc,0.4719401389631213 +story_cloze_2016,2,Story Continuation and Options,acc,0.4740780331373597 +story_cloze_2016,2,median,accuracy,0.4754142169962587 +story_cloze_2016,3,Answer Given options,acc,0.4681988241582042 +story_cloze_2016,3,Choose Story Ending,acc,0.4751469802244789 +story_cloze_2016,3,Novel Correct Ending,acc,0.4692677712453234 +story_cloze_2016,3,Story Continuation and Options,acc,0.467129877071085 +story_cloze_2016,3,median,accuracy,0.46873329770176375 +story_cloze_2016,4,Answer Given options,acc,0.467129877071085 +story_cloze_2016,4,Choose Story Ending,acc,0.467129877071085 +story_cloze_2016,4,Novel Correct Ending,acc,0.4660609299839658 +story_cloze_2016,4,Story Continuation and Options,acc,0.46392303580972744 +story_cloze_2016,4,median,accuracy,0.4665954035275254 +story_cloze_2016,5,Answer Given options,acc,0.46392303580972744 +story_cloze_2016,5,Choose Story Ending,acc,0.45911277391769106 +story_cloze_2016,5,Novel Correct Ending,acc,0.4580438268305719 +story_cloze_2016,5,Story Continuation and Options,acc,0.4537680384820951 +story_cloze_2016,5,median,accuracy,0.4585783003741315 +story_cloze_2016,5,average,multiple,0.4732763228220203 +superglue_rte,0,GPT-3 style,acc,0.5342960288808665 +superglue_rte,0,MNLI crowdsource,acc,0.5270758122743683 +superglue_rte,0,does it follow that,acc,0.5054151624548736 +superglue_rte,0,guaranteed true,acc,0.5270758122743683 +superglue_rte,0,should assume,acc,0.5270758122743683 +superglue_rte,0,median,accuracy,0.5270758122743683 +superglue_rte,1,GPT-3 style,acc,0.4981949458483754 +superglue_rte,1,MNLI crowdsource,acc,0.5306859205776173 +superglue_rte,1,does it follow that,acc,0.49458483754512633 +superglue_rte,1,guaranteed true,acc,0.48375451263537905 +superglue_rte,1,should assume,acc,0.4981949458483754 +superglue_rte,1,median,accuracy,0.4981949458483754 +superglue_rte,2,GPT-3 style,acc,0.5234657039711191 +superglue_rte,2,MNLI crowdsource,acc,0.5090252707581228 +superglue_rte,2,does it follow that,acc,0.5054151624548736 +superglue_rte,2,guaranteed true,acc,0.5018050541516246 +superglue_rte,2,should assume,acc,0.5126353790613718 +superglue_rte,2,median,accuracy,0.5090252707581228 +superglue_rte,3,GPT-3 style,acc,0.516245487364621 +superglue_rte,3,MNLI crowdsource,acc,0.5234657039711191 +superglue_rte,3,does it follow that,acc,0.5126353790613718 +superglue_rte,3,guaranteed true,acc,0.516245487364621 +superglue_rte,3,should assume,acc,0.5270758122743683 +superglue_rte,3,median,accuracy,0.516245487364621 +superglue_rte,4,GPT-3 style,acc,0.5054151624548736 +superglue_rte,4,MNLI crowdsource,acc,0.516245487364621 +superglue_rte,4,does it follow that,acc,0.5018050541516246 +superglue_rte,4,guaranteed true,acc,0.5126353790613718 +superglue_rte,4,should assume,acc,0.5342960288808665 +superglue_rte,4,median,accuracy,0.5126353790613718 +superglue_rte,5,GPT-3 style,acc,0.5018050541516246 +superglue_rte,5,MNLI crowdsource,acc,0.516245487364621 +superglue_rte,5,does it follow that,acc,0.4981949458483754 +superglue_rte,5,guaranteed true,acc,0.5126353790613718 +superglue_rte,5,should assume,acc,0.5126353790613718 +superglue_rte,5,median,accuracy,0.5126353790613718 +superglue_rte,5,average,multiple,0.5126353790613718 +web_nlg_en,0,PALM_prompt,rouge2_fmeasure,0.04357651166126725 +web_nlg_en,0,explicit-graph-description2,rouge2_fmeasure,0.00024213283343663074 +web_nlg_en,0,implicit-graph-description,rouge2_fmeasure,0.008626127762314056 +web_nlg_en,0,non-explicit-description,rouge2_fmeasure,0.004924022976700059 +web_nlg_en,0,very-explicit-description,rouge2_fmeasure,0.07462288276980816 +web_nlg_en,0,median,rouge2_fmeasure,0.008626127762314056 +web_nlg_en,1,PALM_prompt,rouge2_fmeasure,0.03533725838532431 +web_nlg_en,1,explicit-graph-description2,rouge2_fmeasure,0.014443686344970957 +web_nlg_en,1,implicit-graph-description,rouge2_fmeasure,0.01386135386977246 +web_nlg_en,1,non-explicit-description,rouge2_fmeasure,0.01960777337004029 +web_nlg_en,1,very-explicit-description,rouge2_fmeasure,0.04520576758964237 +web_nlg_en,1,median,rouge2_fmeasure,0.01960777337004029 +web_nlg_en,2,PALM_prompt,rouge2_fmeasure,0.03698279772417711 +web_nlg_en,2,explicit-graph-description2,rouge2_fmeasure,0.04163806201461763 +web_nlg_en,2,implicit-graph-description,rouge2_fmeasure,0.03832506645342158 +web_nlg_en,2,non-explicit-description,rouge2_fmeasure,0.03131581713976908 +web_nlg_en,2,very-explicit-description,rouge2_fmeasure,0.06125938231479426 +web_nlg_en,2,median,rouge2_fmeasure,0.03832506645342158 +web_nlg_en,3,PALM_prompt,rouge2_fmeasure,0.037900350601950995 +web_nlg_en,3,explicit-graph-description2,rouge2_fmeasure,0.05445999669995589 +web_nlg_en,3,implicit-graph-description,rouge2_fmeasure,0.05353042851216683 +web_nlg_en,3,non-explicit-description,rouge2_fmeasure,0.03774742782188923 +web_nlg_en,3,very-explicit-description,rouge2_fmeasure,0.07696626766564611 +web_nlg_en,3,median,rouge2_fmeasure,0.05353042851216683 +web_nlg_en,4,PALM_prompt,rouge2_fmeasure,0.038427620423283494 +web_nlg_en,4,explicit-graph-description2,rouge2_fmeasure,0.06572301772314433 +web_nlg_en,4,implicit-graph-description,rouge2_fmeasure,0.06406636511396212 +web_nlg_en,4,non-explicit-description,rouge2_fmeasure,0.04618308258359416 +web_nlg_en,4,very-explicit-description,rouge2_fmeasure,0.08622184894243098 +web_nlg_en,4,median,rouge2_fmeasure,0.06406636511396212 +web_nlg_en,5,PALM_prompt,rouge2_fmeasure,0.03892365918376217 +web_nlg_en,5,explicit-graph-description2,rouge2_fmeasure,0.07189912423622183 +web_nlg_en,5,implicit-graph-description,rouge2_fmeasure,0.07459291610833325 +web_nlg_en,5,non-explicit-description,rouge2_fmeasure,0.05181468037449851 +web_nlg_en,5,very-explicit-description,rouge2_fmeasure,0.09172527737837707 +web_nlg_en,5,median,rouge2_fmeasure,0.07189912423622183 +web_nlg_en,5,average,multiple,0.04267581424135445 +wiki_lingua_en,0,article_summary_en,rouge2_fmeasure,0.05530555190416877 +wiki_lingua_en,0,rephrase_en,rouge2_fmeasure,0.015045420297771185 +wiki_lingua_en,0,summarize_above_en,rouge2_fmeasure,0.004598565155715411 +wiki_lingua_en,0,tldr_en,rouge2_fmeasure,0.013280003159457142 +wiki_lingua_en,0,write_abstract_en,rouge2_fmeasure,0.0168939526317488 +wiki_lingua_en,0,median,rouge2_fmeasure,0.015045420297771185 +wiki_lingua_en,1,article_summary_en,rouge2_fmeasure,0.03409011634055016 +wiki_lingua_en,1,rephrase_en,rouge2_fmeasure,0.0038137867450023814 +wiki_lingua_en,1,summarize_above_en,rouge2_fmeasure,0.003733269944172192 +wiki_lingua_en,1,tldr_en,rouge2_fmeasure,0.00507966104363529 +wiki_lingua_en,1,write_abstract_en,rouge2_fmeasure,0.006578200350543033 +wiki_lingua_en,1,median,rouge2_fmeasure,0.00507966104363529 +wiki_lingua_en,2,article_summary_en,rouge2_fmeasure,0.02797037755556898 +wiki_lingua_en,2,rephrase_en,rouge2_fmeasure,0.004828784168441771 +wiki_lingua_en,2,summarize_above_en,rouge2_fmeasure,0.005602755335977656 +wiki_lingua_en,2,tldr_en,rouge2_fmeasure,0.013472946625192286 +wiki_lingua_en,2,write_abstract_en,rouge2_fmeasure,0.008686912843235644 +wiki_lingua_en,2,median,rouge2_fmeasure,0.008686912843235644 +wiki_lingua_en,3,article_summary_en,rouge2_fmeasure,0.02198351222980969 +wiki_lingua_en,3,rephrase_en,rouge2_fmeasure,0.00494689889012699 +wiki_lingua_en,3,summarize_above_en,rouge2_fmeasure,0.0065193989842291565 +wiki_lingua_en,3,tldr_en,rouge2_fmeasure,0.015547635018168346 +wiki_lingua_en,3,write_abstract_en,rouge2_fmeasure,0.007238486310418053 +wiki_lingua_en,3,median,rouge2_fmeasure,0.007238486310418053 +wiki_lingua_en,4,article_summary_en,rouge2_fmeasure,0.0071615346459846605 +wiki_lingua_en,4,rephrase_en,rouge2_fmeasure,0.0019833072972918566 +wiki_lingua_en,4,summarize_above_en,rouge2_fmeasure,0.0026853344180586664 +wiki_lingua_en,4,tldr_en,rouge2_fmeasure,0.006755300956624583 +wiki_lingua_en,4,write_abstract_en,rouge2_fmeasure,0.001875948079941924 +wiki_lingua_en,4,median,rouge2_fmeasure,0.0026853344180586664 +wiki_lingua_en,5,article_summary_en,rouge2_fmeasure,0.0011656375598739542 +wiki_lingua_en,5,rephrase_en,rouge2_fmeasure,0.0002762510614131578 +wiki_lingua_en,5,summarize_above_en,rouge2_fmeasure,0.00042158314099139017 +wiki_lingua_en,5,tldr_en,rouge2_fmeasure,0.001215199948152673 +wiki_lingua_en,5,write_abstract_en,rouge2_fmeasure,0.0003122235342379389 +wiki_lingua_en,5,median,rouge2_fmeasure,0.00042158314099139017 +wiki_lingua_en,5,average,multiple,0.006526233009018371 +winogrande,0,Replace,acc,0.4996053670086819 +winogrande,0,True or False,acc,0.494869771112865 +winogrande,0,does underscore refer to,acc,0.494869771112865 +winogrande,0,stand for,acc,0.4940805051302289 +winogrande,0,underscore refer to,acc,0.4940805051302289 +winogrande,0,median,accuracy,0.494869771112865 +winogrande,1,Replace,acc,0.5035516969218626 +winogrande,1,True or False,acc,0.5011838989739542 +winogrande,1,does underscore refer to,acc,0.5209155485398579 +winogrande,1,stand for,acc,0.5059194948697711 +winogrande,1,underscore refer to,acc,0.4988161010260458 +winogrande,1,median,accuracy,0.5035516969218626 +winogrande,2,Replace,acc,0.4996053670086819 +winogrande,2,True or False,acc,0.5098658247829518 +winogrande,2,does underscore refer to,acc,0.49329123914759276 +winogrande,2,stand for,acc,0.5035516969218626 +winogrande,2,underscore refer to,acc,0.5130228887134964 +winogrande,2,median,accuracy,0.5035516969218626 +winogrande,3,Replace,acc,0.4956590370955012 +winogrande,3,True or False,acc,0.5059194948697711 +winogrande,3,does underscore refer to,acc,0.489344909234412 +winogrande,3,stand for,acc,0.5114443567482242 +winogrande,3,underscore refer to,acc,0.5035516969218626 +winogrande,3,median,accuracy,0.5035516969218626 +winogrande,4,Replace,acc,0.4925019731649566 +winogrande,4,True or False,acc,0.5201262825572218 +winogrande,4,does underscore refer to,acc,0.48303078137332284 +winogrande,4,stand for,acc,0.5059194948697711 +winogrande,4,underscore refer to,acc,0.516179952644041 +winogrande,4,median,accuracy,0.5059194948697711 +winogrande,5,Replace,acc,0.4980268350434096 +winogrande,5,True or False,acc,0.5185477505919495 +winogrande,5,does underscore refer to,acc,0.5043409629044988 +winogrande,5,stand for,acc,0.5043409629044988 +winogrande,5,underscore refer to,acc,0.5146014206787688 +winogrande,5,median,accuracy,0.5043409629044988 +winogrande,5,average,multiple,0.5026308866087872 diff --git a/421m3b93b9/eval/merged.json b/421m3b93b9/eval/merged.json new file mode 100644 index 0000000000000000000000000000000000000000..0ff2850d977ec28c4818e74d366e37e3385c78a8 --- /dev/null +++ b/421m3b93b9/eval/merged.json @@ -0,0 +1 @@ +{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.2882702237124178, "bleu_stderr": 0.03507359582313697, "rouge1_fmeasure": 0.09304445819797845, "rouge1_fmeasure_stderr": 0.0021071281123058827, "rouge1_precision": 0.07300904609224831, "rouge1_precision_stderr": 0.0029525045593291944, "rouge1_recall": 0.23319598837092428, "rouge1_recall_stderr": 0.004717928243407737, "rouge2_fmeasure": 0.04357651166126725, "rouge2_fmeasure_stderr": 0.0012628931036486493, "rouge2_precision": 0.031781240194588535, "rouge2_precision_stderr": 0.001647655179664631, "rouge2_recall": 0.11446696473056167, "rouge2_recall_stderr": 0.0030078380901265153, "rougeL_fmeasure": 0.09113938986614295, "rougeL_fmeasure_stderr": 0.002025825990715642, "rougeL_precision": 0.07148927214916825, "rougeL_precision_stderr": 0.0028994443219541085, "rougeL_recall": 0.22962123752434357, "rougeL_recall_stderr": 0.004651057204662988, "rougeLsum_fmeasure": 0.08853812013819903, "rougeLsum_fmeasure_stderr": 0.0019810527750856927, "rougeLsum_precision": 0.06999428575198861, "rougeLsum_precision_stderr": 0.0029010892622887635, "rougeLsum_recall": 0.22168579525487217, "rougeLsum_recall_stderr": 0.0043756801267272015}, "explicit-graph-description2": {"bleu": 0.002413992658676713, "bleu_stderr": 0.00013676206143739094, "rouge1_fmeasure": 0.007735199321992511, "rouge1_fmeasure_stderr": 0.0004929168751900662, "rouge1_precision": 0.007871384048100007, "rouge1_precision_stderr": 0.0008027273679290646, "rouge1_recall": 0.025894899249411275, "rouge1_recall_stderr": 0.001510927848658749, "rouge2_fmeasure": 0.00024213283343663074, "rouge2_fmeasure_stderr": 0.00010293363022896083, "rouge2_precision": 0.00018612440324107684, "rouge2_precision_stderr": 0.00010813827959713304, "rouge2_recall": 0.00113072926486338, "rouge2_recall_stderr": 0.0002538916851940024, "rougeL_fmeasure": 0.007693913912486717, "rougeL_fmeasure_stderr": 0.00047606068305271974, "rougeL_precision": 0.007831916501187445, "rougeL_precision_stderr": 0.0007926431382581877, "rougeL_recall": 0.02584550434779307, "rougeL_recall_stderr": 0.0015047949229976157, "rougeLsum_fmeasure": 0.0054174592644268636, "rougeLsum_fmeasure_stderr": 0.0003711886426354486, "rougeLsum_precision": 0.006437589464226677, "rougeLsum_precision_stderr": 0.0007714572173800608, "rougeLsum_recall": 0.018623470093568916, "rougeLsum_recall_stderr": 0.0011493529601984355}, "implicit-graph-description": {"bleu": 0.138569878297038, "bleu_stderr": 0.031551101184468404, "rouge1_fmeasure": 0.04792939313815056, "rouge1_fmeasure_stderr": 0.0009615050147245499, "rouge1_precision": 0.03724302186557898, "rouge1_precision_stderr": 0.0022152532951271718, "rouge1_recall": 0.22526135818945897, "rouge1_recall_stderr": 0.003344792850841178, "rouge2_fmeasure": 0.008626127762314056, "rouge2_fmeasure_stderr": 0.0004981474293610044, "rouge2_precision": 0.005393881463397369, "rouge2_precision_stderr": 0.0003489838735994459, "rouge2_recall": 0.04305719338313865, "rouge2_recall_stderr": 0.0019680551642618054, "rougeL_fmeasure": 0.046408969912627086, "rougeL_fmeasure_stderr": 0.0008900420023077054, "rougeL_precision": 0.03600954286370912, "rougeL_precision_stderr": 0.0021750052445456717, "rougeL_recall": 0.22113346749553864, "rougeL_recall_stderr": 0.0032963184671457187, "rougeLsum_fmeasure": 0.040241405686779766, "rougeLsum_fmeasure_stderr": 0.0008508436852286362, "rougeLsum_precision": 0.0326382629292867, "rougeLsum_precision_stderr": 0.002191301787071691, "rougeLsum_recall": 0.18954584534668284, "rougeLsum_recall_stderr": 0.0028756146093179826}, "non-explicit-description": {"bleu": 0.10593475044710148, "bleu_stderr": 0.02687963406061457, "rouge1_fmeasure": 0.051963445903168815, "rouge1_fmeasure_stderr": 0.001030164799332613, "rouge1_precision": 0.03974548833329957, "rouge1_precision_stderr": 0.0016187665175497782, "rouge1_recall": 0.14319286698789227, "rouge1_recall_stderr": 0.002689949685516924, "rouge2_fmeasure": 0.004924022976700059, "rouge2_fmeasure_stderr": 0.00046504584059277863, "rouge2_precision": 0.0032603459694508664, "rouge2_precision_stderr": 0.00035703887248090323, "rouge2_recall": 0.015671514326625717, "rouge2_recall_stderr": 0.001194008851035889, "rougeL_fmeasure": 0.04746954821622165, "rougeL_fmeasure_stderr": 0.0008839674059173651, "rougeL_precision": 0.03627088781319514, "rougeL_precision_stderr": 0.0015426070426077998, "rougeL_recall": 0.1339405385147445, "rougeL_recall_stderr": 0.0025465644416711453, "rougeLsum_fmeasure": 0.04700320033377673, "rougeLsum_fmeasure_stderr": 0.0009162627771699139, "rougeLsum_precision": 0.036598894332640367, "rougeLsum_precision_stderr": 0.0015865773575606916, "rougeLsum_recall": 0.12773491888135802, "rougeLsum_recall_stderr": 0.0022633071599434925}, "very-explicit-description": {"bleu": 0.80522341763869, "bleu_stderr": 0.08331054875537132, "rouge1_fmeasure": 0.1845095102209193, "rouge1_fmeasure_stderr": 0.0022693042573866838, "rouge1_precision": 0.11575198382455341, "rouge1_precision_stderr": 0.0017409474424184654, "rouge1_recall": 0.608459061007921, "rouge1_recall_stderr": 0.003019908683780843, "rouge2_fmeasure": 0.07462288276980816, "rouge2_fmeasure_stderr": 0.0013694868585983554, "rouge2_precision": 0.04666714418190469, "rouge2_precision_stderr": 0.0009925004787402806, "rouge2_recall": 0.25929817858149656, "rouge2_recall_stderr": 0.0031405181722228706, "rougeL_fmeasure": 0.16027950358425136, "rougeL_fmeasure_stderr": 0.0016115627858449338, "rougeL_precision": 0.09923197095834116, "rougeL_precision_stderr": 0.0012283545567891168, "rougeL_recall": 0.5587128288782699, "rougeL_recall_stderr": 0.003317057185320759, "rougeLsum_fmeasure": 0.15437018471820735, "rougeLsum_fmeasure_stderr": 0.0020528117868010066, "rougeLsum_precision": 0.09697095057432645, "rougeLsum_precision_stderr": 0.0015588062714270727, "rougeLsum_recall": 0.5092192403982401, "rougeLsum_recall_stderr": 0.0028311576287597846}}, "1": {"PALM_prompt": {"bleu": 0.22276279918601394, "bleu_stderr": 0.018133211573574757, "rouge1_fmeasure": 0.0827185269757938, "rouge1_fmeasure_stderr": 0.001999403821307096, "rouge1_precision": 0.06067991294954199, "rouge1_precision_stderr": 0.002071772799498889, "rouge1_recall": 0.20293836364892254, "rouge1_recall_stderr": 0.004213962706134935, "rouge2_fmeasure": 0.03533725838532431, "rouge2_fmeasure_stderr": 0.0011679547214428377, "rouge2_precision": 0.02515093170386624, "rouge2_precision_stderr": 0.0012657693333304634, "rouge2_recall": 0.0927272131857222, "rouge2_recall_stderr": 0.00270796998310677, "rougeL_fmeasure": 0.07920096600543666, "rougeL_fmeasure_stderr": 0.0018627056924898366, "rougeL_precision": 0.05782243575115753, "rougeL_precision_stderr": 0.0019660354949123677, "rougeL_recall": 0.19744065879364792, "rougeL_recall_stderr": 0.004113784957628094, "rougeLsum_fmeasure": 0.07922447831134258, "rougeLsum_fmeasure_stderr": 0.0018815454632281374, "rougeLsum_precision": 0.05802381954191155, "rougeLsum_precision_stderr": 0.0019924692015719286, "rougeLsum_recall": 0.19618466537860657, "rougeLsum_recall_stderr": 0.0040253079050866485}, "explicit-graph-description2": {"bleu": 0.7346171507567223, "bleu_stderr": 0.13707913782304798, "rouge1_fmeasure": 0.14455688747960732, "rouge1_fmeasure_stderr": 0.0018065881001650948, "rouge1_precision": 0.17162164691878115, "rouge1_precision_stderr": 0.002541153433910131, "rouge1_recall": 0.1570833115237782, "rouge1_recall_stderr": 0.0023628047156862182, "rouge2_fmeasure": 0.014443686344970957, "rouge2_fmeasure_stderr": 0.0008315132954917715, "rouge2_precision": 0.017746162480695066, "rouge2_precision_stderr": 0.0011795108909179546, "rouge2_recall": 0.01659075032220689, "rouge2_recall_stderr": 0.0010082231571640825, "rougeL_fmeasure": 0.12055575191673172, "rougeL_fmeasure_stderr": 0.0014352825043199523, "rougeL_precision": 0.14445360743779065, "rougeL_precision_stderr": 0.0021746805211461384, "rougeL_recall": 0.13201397388417854, "rougeL_recall_stderr": 0.0019716702901784876, "rougeLsum_fmeasure": 0.12789813539780287, "rougeLsum_fmeasure_stderr": 0.0015529949122606935, "rougeLsum_precision": 0.1529221545748428, "rougeLsum_precision_stderr": 0.002295493453246678, "rougeLsum_recall": 0.13941491139639123, "rougeLsum_recall_stderr": 0.0020642758193953298}, "implicit-graph-description": {"bleu": 0.7190193263389013, "bleu_stderr": 0.13634910774619252, "rouge1_fmeasure": 0.14139180219702063, "rouge1_fmeasure_stderr": 0.001814619491045361, "rouge1_precision": 0.1677909378471085, "rouge1_precision_stderr": 0.0025279575952143075, "rouge1_recall": 0.1557256533318373, "rouge1_recall_stderr": 0.0024294408093670523, "rouge2_fmeasure": 0.01386135386977246, "rouge2_fmeasure_stderr": 0.0007977730891733734, "rouge2_precision": 0.016973478974085843, "rouge2_precision_stderr": 0.0011314265139906986, "rouge2_recall": 0.01638165201377114, "rouge2_recall_stderr": 0.0009960548800777898, "rougeL_fmeasure": 0.11787997771951876, "rougeL_fmeasure_stderr": 0.0014405006728974714, "rougeL_precision": 0.14118769936973508, "rougeL_precision_stderr": 0.0021616686394079765, "rougeL_recall": 0.1311490160490549, "rougeL_recall_stderr": 0.0020570345011630387, "rougeLsum_fmeasure": 0.12499033357696115, "rougeLsum_fmeasure_stderr": 0.0015650259493247992, "rougeLsum_precision": 0.14939682437853644, "rougeLsum_precision_stderr": 0.0022883954744429844, "rougeLsum_recall": 0.1379569195179203, "rougeLsum_recall_stderr": 0.002111952939893884}, "non-explicit-description": {"bleu": 0.866182823458432, "bleu_stderr": 0.12067272006028423, "rouge1_fmeasure": 0.15066523178744332, "rouge1_fmeasure_stderr": 0.001954438625710324, "rouge1_precision": 0.1735967063811906, "rouge1_precision_stderr": 0.0026270802204174095, "rouge1_recall": 0.17887650999515012, "rouge1_recall_stderr": 0.0031318162204511425, "rouge2_fmeasure": 0.01960777337004029, "rouge2_fmeasure_stderr": 0.001029143211904409, "rouge2_precision": 0.021433820753724266, "rouge2_precision_stderr": 0.001247407681297529, "rouge2_recall": 0.029129370749806007, "rouge2_recall_stderr": 0.0016832821472482552, "rougeL_fmeasure": 0.12623806450553654, "rougeL_fmeasure_stderr": 0.0016066368664537727, "rougeL_precision": 0.14613868593964888, "rougeL_precision_stderr": 0.002258852219739637, "rougeL_recall": 0.15296643190709636, "rougeL_recall_stderr": 0.002859088570123784, "rougeLsum_fmeasure": 0.13299010686343601, "rougeLsum_fmeasure_stderr": 0.001711708966298464, "rougeLsum_precision": 0.15418999276855516, "rougeLsum_precision_stderr": 0.002386058978805089, "rougeLsum_recall": 0.15812304797391522, "rougeLsum_recall_stderr": 0.0027464038170145967}, "very-explicit-description": {"bleu": 0.9786465584605349, "bleu_stderr": 0.14122810214566986, "rouge1_fmeasure": 0.1835504434103257, "rouge1_fmeasure_stderr": 0.002742918027631955, "rouge1_precision": 0.19174924772721366, "rouge1_precision_stderr": 0.0032940489896208926, "rouge1_recall": 0.2698784746776444, "rouge1_recall_stderr": 0.004773612866682941, "rouge2_fmeasure": 0.04520576758964237, "rouge2_fmeasure_stderr": 0.0018353621819071602, "rouge2_precision": 0.04272035087355504, "rouge2_precision_stderr": 0.0019901580959531236, "rouge2_recall": 0.08265565051963014, "rouge2_recall_stderr": 0.0030886698848430383, "rougeL_fmeasure": 0.15410415993634588, "rougeL_fmeasure_stderr": 0.0022370627269454606, "rougeL_precision": 0.1601819681970939, "rougeL_precision_stderr": 0.0027461365015910427, "rougeL_recall": 0.23680658224270798, "rougeL_recall_stderr": 0.004517480324960939, "rougeLsum_fmeasure": 0.16046862402135503, "rougeLsum_fmeasure_stderr": 0.002398180973300977, "rougeLsum_precision": 0.16856045163213934, "rougeLsum_precision_stderr": 0.00294994820031969, "rougeLsum_recall": 0.2363719127409182, "rougeLsum_recall_stderr": 0.004152500838774223}}, "2": {"PALM_prompt": {"bleu": 0.22816452014689217, "bleu_stderr": 0.021011094086360756, "rouge1_fmeasure": 0.0888316472488794, "rouge1_fmeasure_stderr": 0.002008077222359181, "rouge1_precision": 0.0643252880050605, "rouge1_precision_stderr": 0.001873211164048415, "rouge1_recall": 0.21568616317061653, "rouge1_recall_stderr": 0.004082948724364347, "rouge2_fmeasure": 0.03698279772417711, "rouge2_fmeasure_stderr": 0.0011212628433211664, "rouge2_precision": 0.02624513151161159, "rouge2_precision_stderr": 0.001151855832984562, "rouge2_recall": 0.09761833567947041, "rouge2_recall_stderr": 0.0026995300080965585, "rougeL_fmeasure": 0.08454134203955807, "rougeL_fmeasure_stderr": 0.0018430886624515794, "rougeL_precision": 0.0606248912817486, "rougeL_precision_stderr": 0.001701220213613193, "rougeL_recall": 0.20937007549926187, "rougeL_recall_stderr": 0.003993668186702462, "rougeLsum_fmeasure": 0.08484366265533932, "rougeLsum_fmeasure_stderr": 0.0018647506310172767, "rougeLsum_precision": 0.06105372863643947, "rougeLsum_precision_stderr": 0.001737959743755711, "rougeLsum_recall": 0.20931532337002748, "rougeLsum_recall_stderr": 0.003964000228350047}, "explicit-graph-description2": {"bleu": 0.8566894201349882, "bleu_stderr": 0.08624072055130635, "rouge1_fmeasure": 0.18740801320012218, "rouge1_fmeasure_stderr": 0.0026759273447015666, "rouge1_precision": 0.20663907836610496, "rouge1_precision_stderr": 0.0033829599247524127, "rouge1_recall": 0.2479349663972334, "rouge1_recall_stderr": 0.0044131481989255214, "rouge2_fmeasure": 0.04163806201461763, "rouge2_fmeasure_stderr": 0.001744964461999939, "rouge2_precision": 0.044514823553754815, "rouge2_precision_stderr": 0.0020773970237284085, "rouge2_recall": 0.06392575894949451, "rouge2_recall_stderr": 0.002576650238805862, "rougeL_fmeasure": 0.15705135749100313, "rougeL_fmeasure_stderr": 0.0022404431287739728, "rougeL_precision": 0.17383935881323387, "rougeL_precision_stderr": 0.0029141796169836406, "rougeL_recall": 0.21185220120183285, "rougeL_recall_stderr": 0.00391960722018384, "rougeLsum_fmeasure": 0.16490115686406231, "rougeLsum_fmeasure_stderr": 0.0023344806701187824, "rougeLsum_precision": 0.18333789821164648, "rougeLsum_precision_stderr": 0.0030290826006994917, "rougeLsum_recall": 0.2176069260272544, "rougeLsum_recall_stderr": 0.003804234575122432}, "implicit-graph-description": {"bleu": 0.654858159962283, "bleu_stderr": 0.05090283227203148, "rouge1_fmeasure": 0.1718578502584956, "rouge1_fmeasure_stderr": 0.00246372252095823, "rouge1_precision": 0.18587109175652072, "rouge1_precision_stderr": 0.0032528462646382837, "rouge1_recall": 0.25339458245702867, "rouge1_recall_stderr": 0.004577585923235268, "rouge2_fmeasure": 0.03832506645342158, "rouge2_fmeasure_stderr": 0.0014998680640168213, "rouge2_precision": 0.038492631218654094, "rouge2_precision_stderr": 0.0018039997248216703, "rouge2_recall": 0.0713821989527362, "rouge2_recall_stderr": 0.0027007946811370516, "rougeL_fmeasure": 0.14549486942641893, "rougeL_fmeasure_stderr": 0.0020319539502286887, "rougeL_precision": 0.1565380855202379, "rougeL_precision_stderr": 0.002747157296710683, "rougeL_recall": 0.22294560743499395, "rougeL_recall_stderr": 0.004308467347707439, "rougeLsum_fmeasure": 0.14994420152341253, "rougeLsum_fmeasure_stderr": 0.002110161728007287, "rougeLsum_precision": 0.16369817034532635, "rougeLsum_precision_stderr": 0.0028970310154362226, "rougeLsum_recall": 0.22068224654084853, "rougeLsum_recall_stderr": 0.0039045572017400235}, "non-explicit-description": {"bleu": 0.8730659372849066, "bleu_stderr": 0.0967542162395743, "rouge1_fmeasure": 0.16765923923678647, "rouge1_fmeasure_stderr": 0.0022559374477986185, "rouge1_precision": 0.18939988211510023, "rouge1_precision_stderr": 0.003015336802954258, "rouge1_recall": 0.21147314525622352, "rouge1_recall_stderr": 0.003724259557883497, "rouge2_fmeasure": 0.03131581713976908, "rouge2_fmeasure_stderr": 0.0014111826750632776, "rouge2_precision": 0.03379022133984764, "rouge2_precision_stderr": 0.0017843702674752064, "rouge2_recall": 0.04784569405826686, "rouge2_recall_stderr": 0.002202164940653821, "rougeL_fmeasure": 0.14117220655320378, "rougeL_fmeasure_stderr": 0.0018990556078266275, "rougeL_precision": 0.1598064546454118, "rougeL_precision_stderr": 0.002629394580363481, "rougeL_recall": 0.18237543607435028, "rougeL_recall_stderr": 0.0034360872181296307, "rougeLsum_fmeasure": 0.14809597509839093, "rougeLsum_fmeasure_stderr": 0.001972913231852908, "rougeLsum_precision": 0.16876738068884203, "rougeLsum_precision_stderr": 0.0027439682577306787, "rougeLsum_recall": 0.18685899221940896, "rougeLsum_recall_stderr": 0.0032539799319502814}, "very-explicit-description": {"bleu": 0.8880569236257283, "bleu_stderr": 0.10425228469519156, "rouge1_fmeasure": 0.1992879161350844, "rouge1_fmeasure_stderr": 0.002645957854064047, "rouge1_precision": 0.20221739794884294, "rouge1_precision_stderr": 0.0035499636350329366, "rouge1_recall": 0.3332186264589581, "rouge1_recall_stderr": 0.005170101384807238, "rouge2_fmeasure": 0.06125938231479426, "rouge2_fmeasure_stderr": 0.0018555518510493417, "rouge2_precision": 0.05936354342280888, "rouge2_precision_stderr": 0.002387647853920241, "rouge2_recall": 0.1225094044913992, "rouge2_recall_stderr": 0.0034016962379593376, "rougeL_fmeasure": 0.17221690830374237, "rougeL_fmeasure_stderr": 0.0022796430855117032, "rougeL_precision": 0.1735345422105144, "rougeL_precision_stderr": 0.003136069929113322, "rougeL_recall": 0.29921178664666864, "rougeL_recall_stderr": 0.00498953624810007, "rougeLsum_fmeasure": 0.17513713323826788, "rougeLsum_fmeasure_stderr": 0.0023508381923365734, "rougeLsum_precision": 0.17949949840259782, "rougeLsum_precision_stderr": 0.003267322153420465, "rougeLsum_recall": 0.29229470206548336, "rougeLsum_recall_stderr": 0.004488431177710736}}, "3": {"PALM_prompt": {"bleu": 0.21668033919612437, "bleu_stderr": 0.020179750003043416, "rouge1_fmeasure": 0.09037007800347752, "rouge1_fmeasure_stderr": 0.0021075393335480913, "rouge1_precision": 0.06599850329511878, "rouge1_precision_stderr": 0.0020196888536449255, "rouge1_recall": 0.2189549242330715, "rouge1_recall_stderr": 0.00402494120221226, "rouge2_fmeasure": 0.037900350601950995, "rouge2_fmeasure_stderr": 0.0011762008290810827, "rouge2_precision": 0.026861010489235518, "rouge2_precision_stderr": 0.0010411924138277121, "rouge2_recall": 0.09848799682900536, "rouge2_recall_stderr": 0.002619448977397938, "rougeL_fmeasure": 0.0854553995007257, "rougeL_fmeasure_stderr": 0.0018898385438172103, "rougeL_precision": 0.0616752271189791, "rougeL_precision_stderr": 0.0017718026569788809, "rougeL_recall": 0.2115279407271533, "rougeL_recall_stderr": 0.0038925777592653194, "rougeLsum_fmeasure": 0.08596309183671783, "rougeLsum_fmeasure_stderr": 0.001927157623088893, "rougeLsum_precision": 0.0623910245818171, "rougeLsum_precision_stderr": 0.0018474876713692014, "rougeLsum_recall": 0.2116287101661098, "rougeLsum_recall_stderr": 0.0038714328117695138}, "explicit-graph-description2": {"bleu": 1.0569147515296082, "bleu_stderr": 0.0894097345506189, "rouge1_fmeasure": 0.20662215475852175, "rouge1_fmeasure_stderr": 0.0029093584177742257, "rouge1_precision": 0.23700393129285693, "rouge1_precision_stderr": 0.003998832100987239, "rouge1_recall": 0.26444744204782306, "rouge1_recall_stderr": 0.004491563559631609, "rouge2_fmeasure": 0.05445999669995589, "rouge2_fmeasure_stderr": 0.00197546840586398, "rouge2_precision": 0.0618205621459243, "rouge2_precision_stderr": 0.0025531310938124367, "rouge2_recall": 0.07796583472925955, "rouge2_recall_stderr": 0.0027407400714859207, "rougeL_fmeasure": 0.1731669889234156, "rougeL_fmeasure_stderr": 0.0024412054531090356, "rougeL_precision": 0.1993414050245294, "rougeL_precision_stderr": 0.0034880359309727806, "rougeL_recall": 0.2262831386525155, "rougeL_recall_stderr": 0.004000931690515669, "rougeLsum_fmeasure": 0.18190324751556092, "rougeLsum_fmeasure_stderr": 0.002538737343530949, "rougeLsum_precision": 0.21007336129721205, "rougeLsum_precision_stderr": 0.003603119181953105, "rougeLsum_recall": 0.23246013837952773, "rougeLsum_recall_stderr": 0.003889246478806612}, "implicit-graph-description": {"bleu": 0.8662810235466556, "bleu_stderr": 0.09404503161396437, "rouge1_fmeasure": 0.19757579221778704, "rouge1_fmeasure_stderr": 0.002740581812349554, "rouge1_precision": 0.21630507113127517, "rouge1_precision_stderr": 0.0037635681346209204, "rouge1_recall": 0.29385220234946363, "rouge1_recall_stderr": 0.004939943721033626, "rouge2_fmeasure": 0.05353042851216683, "rouge2_fmeasure_stderr": 0.0018154897675158883, "rouge2_precision": 0.05540012459456432, "rouge2_precision_stderr": 0.002226210322926932, "rouge2_recall": 0.09790333465592813, "rouge2_recall_stderr": 0.003133062562474596, "rougeL_fmeasure": 0.1686567646585531, "rougeL_fmeasure_stderr": 0.00233205958797479, "rougeL_precision": 0.1839111737113415, "rougeL_precision_stderr": 0.0032708663113493845, "rougeL_recall": 0.2610670692827167, "rougeL_recall_stderr": 0.004730435390915318, "rougeLsum_fmeasure": 0.17281728476431374, "rougeLsum_fmeasure_stderr": 0.002423817934865248, "rougeLsum_precision": 0.19108993104157018, "rougeLsum_precision_stderr": 0.00343247374642446, "rougeLsum_recall": 0.25510045795061914, "rougeLsum_recall_stderr": 0.004229656468015747}, "non-explicit-description": {"bleu": 1.2329509109603611, "bleu_stderr": 0.17037107794770673, "rouge1_fmeasure": 0.17604709161678792, "rouge1_fmeasure_stderr": 0.0024207021911546002, "rouge1_precision": 0.20206518395397247, "rouge1_precision_stderr": 0.0033815561981644514, "rouge1_recall": 0.22055576804184665, "rouge1_recall_stderr": 0.0038689842229781995, "rouge2_fmeasure": 0.03774742782188923, "rouge2_fmeasure_stderr": 0.0016476754720179338, "rouge2_precision": 0.042414826534170676, "rouge2_precision_stderr": 0.002194212193720834, "rouge2_recall": 0.056638379731478804, "rouge2_recall_stderr": 0.0024560943269569097, "rougeL_fmeasure": 0.1484395491444522, "rougeL_fmeasure_stderr": 0.0020503728880959028, "rougeL_precision": 0.17012750089049355, "rougeL_precision_stderr": 0.002909118143288585, "rougeL_recall": 0.19153932535514462, "rougeL_recall_stderr": 0.0036627963511066176, "rougeLsum_fmeasure": 0.15595031738973972, "rougeLsum_fmeasure_stderr": 0.0021234132418142156, "rougeLsum_precision": 0.18026184477100235, "rougeLsum_precision_stderr": 0.0030566342359595712, "rougeLsum_recall": 0.19503635904047142, "rougeLsum_recall_stderr": 0.00336915844462403}, "very-explicit-description": {"bleu": 0.9859334350527383, "bleu_stderr": 0.09896199153842244, "rouge1_fmeasure": 0.21408595760940946, "rouge1_fmeasure_stderr": 0.002783818736006089, "rouge1_precision": 0.22015440449805468, "rouge1_precision_stderr": 0.004191773103751877, "rouge1_recall": 0.36592032189171225, "rouge1_recall_stderr": 0.005068220370589984, "rouge2_fmeasure": 0.07696626766564611, "rouge2_fmeasure_stderr": 0.0020398698531970743, "rouge2_precision": 0.07910542573583534, "rouge2_precision_stderr": 0.0029902820037111502, "rouge2_recall": 0.1491354669018872, "rouge2_recall_stderr": 0.003459225616571808, "rougeL_fmeasure": 0.18711621313587448, "rougeL_fmeasure_stderr": 0.0024249095985234463, "rougeL_precision": 0.19072950772310418, "rougeL_precision_stderr": 0.003726367705712794, "rougeL_recall": 0.33282521900185674, "rougeL_recall_stderr": 0.004954398958565515, "rougeLsum_fmeasure": 0.1889169148591612, "rougeLsum_fmeasure_stderr": 0.0025246051964903276, "rougeLsum_precision": 0.1958992768265335, "rougeLsum_precision_stderr": 0.003884089051877238, "rougeLsum_recall": 0.3218771452899728, "rougeLsum_recall_stderr": 0.004412820950063993}}, "4": {"PALM_prompt": {"bleu": 0.22324841354029434, "bleu_stderr": 0.012884365211201858, "rouge1_fmeasure": 0.08984024388721441, "rouge1_fmeasure_stderr": 0.002049686525188311, "rouge1_precision": 0.06502648081363527, "rouge1_precision_stderr": 0.0019568795906677195, "rouge1_recall": 0.22314967057311585, "rouge1_recall_stderr": 0.004060178019176997, "rouge2_fmeasure": 0.038427620423283494, "rouge2_fmeasure_stderr": 0.0011342309564967815, "rouge2_precision": 0.027172974346249407, "rouge2_precision_stderr": 0.0010775269042031367, "rouge2_recall": 0.10278841213516382, "rouge2_recall_stderr": 0.0026896302440292856, "rougeL_fmeasure": 0.08475169911603465, "rougeL_fmeasure_stderr": 0.0018041950412597118, "rougeL_precision": 0.06051581313878435, "rougeL_precision_stderr": 0.001686918901782139, "rougeL_recall": 0.21546541192297525, "rougeL_recall_stderr": 0.0039050941983854084, "rougeLsum_fmeasure": 0.08562046048144208, "rougeLsum_fmeasure_stderr": 0.0018622202648950923, "rougeLsum_precision": 0.06149322300624985, "rougeLsum_precision_stderr": 0.0017642592919849167, "rougeLsum_recall": 0.21601509705224456, "rougeLsum_recall_stderr": 0.003902368298687872}, "explicit-graph-description2": {"bleu": 1.1744154279568062, "bleu_stderr": 0.10900900384288126, "rouge1_fmeasure": 0.21768757196984853, "rouge1_fmeasure_stderr": 0.0030964308114536637, "rouge1_precision": 0.24343442215612912, "rouge1_precision_stderr": 0.004290336159466549, "rouge1_recall": 0.2937677188486643, "rouge1_recall_stderr": 0.00476022029269311, "rouge2_fmeasure": 0.06572301772314433, "rouge2_fmeasure_stderr": 0.0022002247062358235, "rouge2_precision": 0.07382521753054258, "rouge2_precision_stderr": 0.002822725067559204, "rouge2_recall": 0.09629906393146742, "rouge2_recall_stderr": 0.0030384383273633826, "rougeL_fmeasure": 0.18281448217767138, "rougeL_fmeasure_stderr": 0.002566640286607954, "rougeL_precision": 0.2052733017686618, "rougeL_precision_stderr": 0.0037268495898633647, "rougeL_recall": 0.252355975266905, "rougeL_recall_stderr": 0.004227144384953933, "rougeLsum_fmeasure": 0.1915680837153, "rougeLsum_fmeasure_stderr": 0.0026965258074827755, "rougeLsum_precision": 0.21562448887139193, "rougeLsum_precision_stderr": 0.003855934210118673, "rougeLsum_recall": 0.2578416353472927, "rougeLsum_recall_stderr": 0.004098132845796672}, "implicit-graph-description": {"bleu": 0.8327592530541046, "bleu_stderr": 0.08252044356912364, "rouge1_fmeasure": 0.20994644193209497, "rouge1_fmeasure_stderr": 0.002856480485934521, "rouge1_precision": 0.22591578566077025, "rouge1_precision_stderr": 0.0040744177303127975, "rouge1_recall": 0.3271371159734268, "rouge1_recall_stderr": 0.004954912621561014, "rouge2_fmeasure": 0.06406636511396212, "rouge2_fmeasure_stderr": 0.001978008075438107, "rouge2_precision": 0.06610289029069367, "rouge2_precision_stderr": 0.0024587911594638476, "rouge2_recall": 0.11815894609420728, "rouge2_recall_stderr": 0.003294870975442443, "rougeL_fmeasure": 0.1795827877529302, "rougeL_fmeasure_stderr": 0.0024101179259044926, "rougeL_precision": 0.19179087245553803, "rougeL_precision_stderr": 0.0034654596797486763, "rougeL_recall": 0.29163613239456493, "rougeL_recall_stderr": 0.004772453186076372, "rougeLsum_fmeasure": 0.18295052341283213, "rougeLsum_fmeasure_stderr": 0.0025224970561372752, "rougeLsum_precision": 0.1981303722652317, "rougeLsum_precision_stderr": 0.0036291877325131637, "rougeLsum_recall": 0.28411489421280556, "rougeLsum_recall_stderr": 0.004268909617622095}, "non-explicit-description": {"bleu": 1.0792721560875334, "bleu_stderr": 0.11897941335086845, "rouge1_fmeasure": 0.1877008682716093, "rouge1_fmeasure_stderr": 0.0025984841921980026, "rouge1_precision": 0.21304666535883363, "rouge1_precision_stderr": 0.0035447207581696576, "rouge1_recall": 0.24044196270498344, "rouge1_recall_stderr": 0.0041272020875937985, "rouge2_fmeasure": 0.04618308258359416, "rouge2_fmeasure_stderr": 0.001794744112452255, "rouge2_precision": 0.05150741153389857, "rouge2_precision_stderr": 0.002310685514094819, "rouge2_recall": 0.06873712069242928, "rouge2_recall_stderr": 0.002686212129477722, "rougeL_fmeasure": 0.15952145174338822, "rougeL_fmeasure_stderr": 0.002218483952497624, "rougeL_precision": 0.18100550700598406, "rougeL_precision_stderr": 0.00309059853405147, "rougeL_recall": 0.2097555633903283, "rougeL_recall_stderr": 0.0038640348862670876, "rougeLsum_fmeasure": 0.16563209206374943, "rougeLsum_fmeasure_stderr": 0.002290227287484681, "rougeLsum_precision": 0.18979889801871716, "rougeLsum_precision_stderr": 0.003258591536788394, "rougeLsum_recall": 0.2114319997150186, "rougeLsum_recall_stderr": 0.0035621450472765647}, "very-explicit-description": {"bleu": 0.970241931626179, "bleu_stderr": 0.09819030681966434, "rouge1_fmeasure": 0.22549673923508326, "rouge1_fmeasure_stderr": 0.002910775643802205, "rouge1_precision": 0.23228499942428968, "rouge1_precision_stderr": 0.004398241056245007, "rouge1_recall": 0.38453431214088857, "rouge1_recall_stderr": 0.005025202128638685, "rouge2_fmeasure": 0.08622184894243098, "rouge2_fmeasure_stderr": 0.002115033774398341, "rouge2_precision": 0.08911780913376037, "rouge2_precision_stderr": 0.0031127641641959516, "rouge2_recall": 0.16391169232553854, "rouge2_recall_stderr": 0.003564158188179595, "rougeL_fmeasure": 0.19820026126581727, "rougeL_fmeasure_stderr": 0.002503140302475953, "rougeL_precision": 0.20268160388419554, "rougeL_precision_stderr": 0.0039238158298998795, "rougeL_recall": 0.3506485664858236, "rougeL_recall_stderr": 0.004886831999021539, "rougeLsum_fmeasure": 0.19907520284773375, "rougeLsum_fmeasure_stderr": 0.002614354718088979, "rougeLsum_precision": 0.20731340856698283, "rougeLsum_precision_stderr": 0.004088067992288368, "rougeLsum_recall": 0.33831857306922314, "rougeLsum_recall_stderr": 0.004362271840091005}}, "5": {"PALM_prompt": {"bleu": 0.21464230162703427, "bleu_stderr": 0.01244691129274461, "rouge1_fmeasure": 0.09216278427137457, "rouge1_fmeasure_stderr": 0.002102114353680242, "rouge1_precision": 0.06952443270444716, "rouge1_precision_stderr": 0.0022809171687925307, "rouge1_recall": 0.23024280021949023, "rouge1_recall_stderr": 0.00409858662928981, "rouge2_fmeasure": 0.03892365918376217, "rouge2_fmeasure_stderr": 0.0011826072971332408, "rouge2_precision": 0.027750881647517683, "rouge2_precision_stderr": 0.0011006386822245205, "rouge2_recall": 0.10600678669436031, "rouge2_recall_stderr": 0.002763944580059492, "rougeL_fmeasure": 0.08717550041439592, "rougeL_fmeasure_stderr": 0.0018759391818764337, "rougeL_precision": 0.06485734355722127, "rougeL_precision_stderr": 0.002020231716412655, "rougeL_recall": 0.22257612852322436, "rougeL_recall_stderr": 0.003940687874091731, "rougeLsum_fmeasure": 0.08796230830100418, "rougeLsum_fmeasure_stderr": 0.0019209922626217265, "rougeLsum_precision": 0.06592417348285784, "rougeLsum_precision_stderr": 0.0021091163919465493, "rougeLsum_recall": 0.22298794088967588, "rougeLsum_recall_stderr": 0.003928367080650771}, "explicit-graph-description2": {"bleu": 1.2744890026821296, "bleu_stderr": 0.09553029750807113, "rouge1_fmeasure": 0.22576005910143196, "rouge1_fmeasure_stderr": 0.0032791573262992177, "rouge1_precision": 0.25749968628071634, "rouge1_precision_stderr": 0.004557872484881917, "rouge1_recall": 0.2952708397989195, "rouge1_recall_stderr": 0.004728252484609096, "rouge2_fmeasure": 0.07189912423622183, "rouge2_fmeasure_stderr": 0.0023282015023082664, "rouge2_precision": 0.08269685100109506, "rouge2_precision_stderr": 0.003027333731786083, "rouge2_recall": 0.10110655349024573, "rouge2_recall_stderr": 0.0031054606964476387, "rougeL_fmeasure": 0.19074926578003074, "rougeL_fmeasure_stderr": 0.0027348190562132136, "rougeL_precision": 0.21853685082560628, "rougeL_precision_stderr": 0.0039871118588556366, "rougeL_recall": 0.25492080968482705, "rougeL_recall_stderr": 0.00420711638229053, "rougeLsum_fmeasure": 0.19945385414430314, "rougeLsum_fmeasure_stderr": 0.0028579749339794932, "rougeLsum_precision": 0.22916016865925895, "rougeLsum_precision_stderr": 0.00411577700341045, "rougeLsum_recall": 0.260297323377531, "rougeLsum_recall_stderr": 0.00409556008633347}, "implicit-graph-description": {"bleu": 0.9864896153661107, "bleu_stderr": 0.1114488450591458, "rouge1_fmeasure": 0.2239773930782515, "rouge1_fmeasure_stderr": 0.003099702038886262, "rouge1_precision": 0.24687269679032836, "rouge1_precision_stderr": 0.004501369815547214, "rouge1_recall": 0.3404419977444704, "rouge1_recall_stderr": 0.005025782336662627, "rouge2_fmeasure": 0.07459291610833325, "rouge2_fmeasure_stderr": 0.0021594277862978053, "rouge2_precision": 0.08027601856562787, "rouge2_precision_stderr": 0.0028587155748841155, "rouge2_recall": 0.12944258320105298, "rouge2_recall_stderr": 0.0033520136379546575, "rougeL_fmeasure": 0.1924435416395898, "rougeL_fmeasure_stderr": 0.0026000922872309144, "rougeL_precision": 0.21029176429912327, "rougeL_precision_stderr": 0.003853857396675998, "rougeL_recall": 0.3046329495523381, "rougeL_recall_stderr": 0.004807937355834806, "rougeLsum_fmeasure": 0.19609167052374815, "rougeLsum_fmeasure_stderr": 0.0027163034898814884, "rougeLsum_precision": 0.21773348211753543, "rougeLsum_precision_stderr": 0.004056669090372054, "rougeLsum_recall": 0.29668821393068523, "rougeLsum_recall_stderr": 0.004287898580495838}, "non-explicit-description": {"bleu": 1.0840527290308135, "bleu_stderr": 0.1285257175145367, "rouge1_fmeasure": 0.1937895542833093, "rouge1_fmeasure_stderr": 0.0026930519639634374, "rouge1_precision": 0.22377177397658685, "rouge1_precision_stderr": 0.003751306840404075, "rouge1_recall": 0.24374911073515992, "rouge1_recall_stderr": 0.004063940123637665, "rouge2_fmeasure": 0.05181468037449851, "rouge2_fmeasure_stderr": 0.0019301208843236668, "rouge2_precision": 0.05842395909971782, "rouge2_precision_stderr": 0.002544233000490118, "rouge2_recall": 0.07447247779662981, "rouge2_recall_stderr": 0.0027180704781684995, "rougeL_fmeasure": 0.16586855159557498, "rougeL_fmeasure_stderr": 0.002321441985077457, "rougeL_precision": 0.19087203826268628, "rougeL_precision_stderr": 0.003283058254228487, "rougeL_recall": 0.21393350174137546, "rougeL_recall_stderr": 0.003813517852998068, "rougeLsum_fmeasure": 0.17256400094312105, "rougeLsum_fmeasure_stderr": 0.002384598354184546, "rougeLsum_precision": 0.2003884829724675, "rougeLsum_precision_stderr": 0.00343390307735665, "rougeLsum_recall": 0.21705758718159215, "rougeLsum_recall_stderr": 0.0035797162130504407}, "very-explicit-description": {"bleu": 1.0632385816538097, "bleu_stderr": 0.108635681810979, "rouge1_fmeasure": 0.22840858338472744, "rouge1_fmeasure_stderr": 0.0030840481426459535, "rouge1_precision": 0.2382691545863073, "rouge1_precision_stderr": 0.004756985829441475, "rouge1_recall": 0.3912072250236538, "rouge1_recall_stderr": 0.004984269579179742, "rouge2_fmeasure": 0.09172527737837707, "rouge2_fmeasure_stderr": 0.0022023809206421522, "rouge2_precision": 0.09843522450433298, "rouge2_precision_stderr": 0.003424552765398845, "rouge2_recall": 0.17269348031155235, "rouge2_recall_stderr": 0.0035758918530598553, "rougeL_fmeasure": 0.2006439166198059, "rougeL_fmeasure_stderr": 0.002601338113671856, "rougeL_precision": 0.20797653399558047, "rougeL_precision_stderr": 0.00422832319942412, "rougeL_recall": 0.35688189171657314, "rougeL_recall_stderr": 0.004844058830738807, "rougeLsum_fmeasure": 0.20278396643749147, "rougeLsum_fmeasure_stderr": 0.002742019476188682, "rougeLsum_precision": 0.21340003515373943, "rougeLsum_precision_stderr": 0.004405460746761557, "rougeLsum_recall": 0.3469582914902356, "rougeLsum_recall_stderr": 0.004377091064495331}}}, "GEM/wiki_lingua_en": {"0": {"article_summary_en": {"bleu": 2.4682328449343904, "bleu_stderr": 0.07088258721604575, "rouge1_fmeasure": 0.23412884345862264, "rouge1_fmeasure_stderr": 0.0018096388944563407, "rouge1_precision": 0.195566960716181, "rouge1_precision_stderr": 0.0019276846426063785, "rouge1_recall": 0.3533886371026647, "rouge1_recall_stderr": 0.0027880868773002996, "rouge2_fmeasure": 0.05530555190416877, "rouge2_fmeasure_stderr": 0.0009620765372106006, "rouge2_precision": 0.04589459114508951, "rouge2_precision_stderr": 0.0008493337249853646, "rouge2_recall": 0.08686815821286678, "rouge2_recall_stderr": 0.0017485584142853405, "rougeL_fmeasure": 0.1577035391779481, "rougeL_fmeasure_stderr": 0.0011540548708147851, "rougeL_precision": 0.12997894688819828, "rougeL_precision_stderr": 0.001176996687844147, "rougeL_recall": 0.2455653248515433, "rougeL_recall_stderr": 0.002216289748634435, "rougeLsum_fmeasure": 0.21698957847628453, "rougeLsum_fmeasure_stderr": 0.001673828218441473, "rougeLsum_precision": 0.18107871658618507, "rougeLsum_precision_stderr": 0.0017806857113047642, "rougeLsum_recall": 0.3283060348710063, "rougeLsum_recall_stderr": 0.002625017894293712}, "rephrase_en": {"bleu": 0.8117389101795618, "bleu_stderr": 0.05120531843865198, "rouge1_fmeasure": 0.1174568672178565, "rouge1_fmeasure_stderr": 0.0016459536455676414, "rouge1_precision": 0.10569868627384524, "rouge1_precision_stderr": 0.0017140526493108679, "rouge1_recall": 0.16204648662100252, "rouge1_recall_stderr": 0.002316216467829637, "rouge2_fmeasure": 0.015045420297771185, "rouge2_fmeasure_stderr": 0.0005981449989858111, "rouge2_precision": 0.013201893034513962, "rouge2_precision_stderr": 0.0005378682826493545, "rouge2_recall": 0.022027771467537875, "rouge2_recall_stderr": 0.0009738896413116423, "rougeL_fmeasure": 0.0992022930965774, "rougeL_fmeasure_stderr": 0.0012654116495173472, "rougeL_precision": 0.08838578365243173, "rougeL_precision_stderr": 0.0013067594648947581, "rougeL_recall": 0.1392947948040508, "rougeL_recall_stderr": 0.0019179440859143518, "rougeLsum_fmeasure": 0.10959697102431157, "rougeLsum_fmeasure_stderr": 0.0015286108227936896, "rougeLsum_precision": 0.09855134328369819, "rougeLsum_precision_stderr": 0.0015934085607222398, "rougeLsum_recall": 0.15144176964309033, "rougeLsum_recall_stderr": 0.002157349066143636}, "summarize_above_en": {"bleu": 0.2519277717730189, "bleu_stderr": 0.03524949351036431, "rouge1_fmeasure": 0.05817807410278456, "rouge1_fmeasure_stderr": 0.0013730134887578534, "rouge1_precision": 0.05321505980023667, "rouge1_precision_stderr": 0.0014181666167610405, "rouge1_recall": 0.07795628718339453, "rouge1_recall_stderr": 0.0018410017875166815, "rouge2_fmeasure": 0.004598565155715411, "rouge2_fmeasure_stderr": 0.0003111709286716547, "rouge2_precision": 0.004212936258690241, "rouge2_precision_stderr": 0.00028227201371374533, "rouge2_recall": 0.006550413011055106, "rouge2_recall_stderr": 0.0005770046318012553, "rougeL_fmeasure": 0.05496385663485581, "rougeL_fmeasure_stderr": 0.0012393700178193036, "rougeL_precision": 0.05005075628972684, "rougeL_precision_stderr": 0.001278959345154331, "rougeL_recall": 0.07412927953859504, "rougeL_recall_stderr": 0.0016956652339899909, "rougeLsum_fmeasure": 0.05462669247662518, "rougeLsum_fmeasure_stderr": 0.001271676260318409, "rougeLsum_precision": 0.04982130748814443, "rougeLsum_precision_stderr": 0.0013143803339713488, "rougeLsum_recall": 0.07363722344726391, "rougeLsum_recall_stderr": 0.0017324048141738725}, "tldr_en": {"bleu": 0.6707270817884038, "bleu_stderr": 0.046602035483089825, "rouge1_fmeasure": 0.11334607060168528, "rouge1_fmeasure_stderr": 0.0016396098775080439, "rouge1_precision": 0.1078207522843226, "rouge1_precision_stderr": 0.001940682197702513, "rouge1_recall": 0.1520153396969911, "rouge1_recall_stderr": 0.002277894036435405, "rouge2_fmeasure": 0.013280003159457142, "rouge2_fmeasure_stderr": 0.000558295558429676, "rouge2_precision": 0.011837859560447648, "rouge2_precision_stderr": 0.0005138331303314764, "rouge2_recall": 0.019458716329622143, "rouge2_recall_stderr": 0.0009420647807959251, "rougeL_fmeasure": 0.09699392119251118, "rougeL_fmeasure_stderr": 0.0012980799468792427, "rougeL_precision": 0.09180182708936059, "rougeL_precision_stderr": 0.0016152505728822433, "rougeL_recall": 0.13192962900825583, "rougeL_recall_stderr": 0.0019204374301591803, "rougeLsum_fmeasure": 0.10617032427066436, "rougeLsum_fmeasure_stderr": 0.0015161029623370764, "rougeLsum_precision": 0.10116224232784549, "rougeLsum_precision_stderr": 0.001831498246711715, "rougeLsum_recall": 0.14236722673055757, "rougeLsum_recall_stderr": 0.0021081023222958317}, "write_abstract_en": {"bleu": 0.8049467835361911, "bleu_stderr": 0.06125790470590714, "rouge1_fmeasure": 0.11287104782454531, "rouge1_fmeasure_stderr": 0.0018302548422649888, "rouge1_precision": 0.1467073059254317, "rouge1_precision_stderr": 0.003923847788182457, "rouge1_recall": 0.1488423584822216, "rouge1_recall_stderr": 0.002514278160277046, "rouge2_fmeasure": 0.0168939526317488, "rouge2_fmeasure_stderr": 0.0006560231719498498, "rouge2_precision": 0.015139213553420103, "rouge2_precision_stderr": 0.0006017762732827434, "rouge2_recall": 0.023991338309341914, "rouge2_recall_stderr": 0.0010741770192485198, "rougeL_fmeasure": 0.09354722719833262, "rougeL_fmeasure_stderr": 0.001367594008196884, "rougeL_precision": 0.12846108969943054, "rougeL_precision_stderr": 0.0037967129632843506, "rougeL_recall": 0.12514947700874288, "rougeL_recall_stderr": 0.002011926521503057, "rougeLsum_fmeasure": 0.10483417861156145, "rougeLsum_fmeasure_stderr": 0.0016823495491907201, "rougeLsum_precision": 0.13919269715957514, "rougeLsum_precision_stderr": 0.003880077948366859, "rougeLsum_recall": 0.13851578235021383, "rougeLsum_recall_stderr": 0.0023319716005974654}}, "1": {"article_summary_en": {"bleu": 1.7919407346163008, "bleu_stderr": 0.0737452533520425, "rouge1_fmeasure": 0.17453230736185904, "rouge1_fmeasure_stderr": 0.001969765354449983, "rouge1_precision": 0.15627750165547535, "rouge1_precision_stderr": 0.001962386369273289, "rouge1_recall": 0.2525742254443488, "rouge1_recall_stderr": 0.003113402494824898, "rouge2_fmeasure": 0.03409011634055016, "rouge2_fmeasure_stderr": 0.0008690874010719925, "rouge2_precision": 0.029169479431573355, "rouge2_precision_stderr": 0.0007882937343141538, "rouge2_recall": 0.0531848239381476, "rouge2_recall_stderr": 0.0015457168877853818, "rougeL_fmeasure": 0.1250045596802973, "rougeL_fmeasure_stderr": 0.0012753773488612319, "rougeL_precision": 0.11201479367079172, "rougeL_precision_stderr": 0.001306085160918015, "rougeL_recall": 0.1848814168046244, "rougeL_recall_stderr": 0.0023307923443449947, "rougeLsum_fmeasure": 0.16303218310550338, "rougeLsum_fmeasure_stderr": 0.0018145396789941985, "rougeLsum_precision": 0.14621744079984547, "rougeLsum_precision_stderr": 0.0018210021156558275, "rougeLsum_recall": 0.23601641233060858, "rougeLsum_recall_stderr": 0.0028953510119446627}, "rephrase_en": {"bleu": 0.2794013007287592, "bleu_stderr": 0.04394092663556765, "rouge1_fmeasure": 0.098994814039191, "rouge1_fmeasure_stderr": 0.0011402494962994437, "rouge1_precision": 0.11390300359943901, "rouge1_precision_stderr": 0.001505310086956201, "rouge1_recall": 0.11050639157282433, "rouge1_recall_stderr": 0.0014435125389142748, "rouge2_fmeasure": 0.0038137867450023814, "rouge2_fmeasure_stderr": 0.00023343889478032686, "rouge2_precision": 0.004517191185289906, "rouge2_precision_stderr": 0.0002871310006425094, "rouge2_recall": 0.004113881151457014, "rouge2_recall_stderr": 0.00027381193246220814, "rougeL_fmeasure": 0.07918587597477968, "rougeL_fmeasure_stderr": 0.0008565313092324011, "rougeL_precision": 0.09172939994661446, "rougeL_precision_stderr": 0.0011916256374520841, "rougeL_recall": 0.089104978321703, "rougeL_recall_stderr": 0.0011511611569130506, "rougeLsum_fmeasure": 0.09563169367500524, "rougeLsum_fmeasure_stderr": 0.001091436945649962, "rougeLsum_precision": 0.10993079553359293, "rougeLsum_precision_stderr": 0.0014392346467215847, "rougeLsum_recall": 0.1069392153189123, "rougeLsum_recall_stderr": 0.0013956438936564995}, "summarize_above_en": {"bleu": 0.23894215568211405, "bleu_stderr": 0.0231127989782631, "rouge1_fmeasure": 0.0987597492588469, "rouge1_fmeasure_stderr": 0.0011303207925802167, "rouge1_precision": 0.11385785104351803, "rouge1_precision_stderr": 0.0014965391184321181, "rouge1_recall": 0.10937667766926965, "rouge1_recall_stderr": 0.0014145590881837738, "rouge2_fmeasure": 0.003733269944172192, "rouge2_fmeasure_stderr": 0.0002255133736408092, "rouge2_precision": 0.004457883873596226, "rouge2_precision_stderr": 0.0002826935523898672, "rouge2_recall": 0.0040283569854367126, "rouge2_recall_stderr": 0.0002662158979064575, "rougeL_fmeasure": 0.07895189836522858, "rougeL_fmeasure_stderr": 0.0008476363984155375, "rougeL_precision": 0.09155580309452313, "rougeL_precision_stderr": 0.0011764557134249975, "rougeL_recall": 0.08815903146004761, "rougeL_recall_stderr": 0.0011271831761762122, "rougeLsum_fmeasure": 0.09547883528709802, "rougeLsum_fmeasure_stderr": 0.0010834332898652644, "rougeLsum_precision": 0.10994991245043519, "rougeLsum_precision_stderr": 0.0014301005338092242, "rougeLsum_recall": 0.10592427428936108, "rougeLsum_recall_stderr": 0.001368238986007311}, "tldr_en": {"bleu": 0.43855817321834095, "bleu_stderr": 0.06688374272014054, "rouge1_fmeasure": 0.10140750562931955, "rouge1_fmeasure_stderr": 0.001200027323440739, "rouge1_precision": 0.1160224630989691, "rouge1_precision_stderr": 0.0015635722100785284, "rouge1_recall": 0.11479872451661574, "rouge1_recall_stderr": 0.0016007866744804707, "rouge2_fmeasure": 0.00507966104363529, "rouge2_fmeasure_stderr": 0.00030717988724990536, "rouge2_precision": 0.005941589755812423, "rouge2_precision_stderr": 0.0004274156364302611, "rouge2_recall": 0.006017596275684403, "rouge2_recall_stderr": 0.00041646260466011385, "rougeL_fmeasure": 0.08108861724066418, "rougeL_fmeasure_stderr": 0.000902890435608752, "rougeL_precision": 0.09349045000409738, "rougeL_precision_stderr": 0.0012461235636124553, "rougeL_recall": 0.09234699285193011, "rougeL_recall_stderr": 0.0012589640727499547, "rougeLsum_fmeasure": 0.09791498603078132, "rougeLsum_fmeasure_stderr": 0.001146504425053145, "rougeLsum_precision": 0.11197455431954438, "rougeLsum_precision_stderr": 0.001497949074925301, "rougeLsum_recall": 0.1110141699775543, "rougeLsum_recall_stderr": 0.0015424239322369367}, "write_abstract_en": {"bleu": 0.6042770786450469, "bleu_stderr": 0.06784193000730189, "rouge1_fmeasure": 0.10581662192060133, "rouge1_fmeasure_stderr": 0.001297467104327135, "rouge1_precision": 0.11672921172744681, "rouge1_precision_stderr": 0.0015455078946896611, "rouge1_recall": 0.12404651186718361, "rouge1_recall_stderr": 0.001833482506124768, "rouge2_fmeasure": 0.006578200350543033, "rouge2_fmeasure_stderr": 0.0004020452136350789, "rouge2_precision": 0.00662318107917187, "rouge2_precision_stderr": 0.00038908144611155763, "rouge2_recall": 0.008569619519959264, "rouge2_recall_stderr": 0.0005860808060358155, "rougeL_fmeasure": 0.08315064354847855, "rougeL_fmeasure_stderr": 0.0009263412660918235, "rougeL_precision": 0.09258137259929677, "rougeL_precision_stderr": 0.0011789964767188995, "rougeL_recall": 0.09781932700181184, "rougeL_recall_stderr": 0.0013635799564556685, "rougeLsum_fmeasure": 0.10191075189261449, "rougeLsum_fmeasure_stderr": 0.0012281012231510622, "rougeLsum_precision": 0.11236796963847627, "rougeLsum_precision_stderr": 0.0014661420025751913, "rougeLsum_recall": 0.11962539469182883, "rougeLsum_recall_stderr": 0.0017515297053630175}}, "2": {"article_summary_en": {"bleu": 1.51129197235676, "bleu_stderr": 0.053033171757604795, "rouge1_fmeasure": 0.15863525455004393, "rouge1_fmeasure_stderr": 0.001916917232761661, "rouge1_precision": 0.14501437881859028, "rouge1_precision_stderr": 0.0019433084591004713, "rouge1_recall": 0.22467032769033468, "rouge1_recall_stderr": 0.0029784346495177407, "rouge2_fmeasure": 0.02797037755556898, "rouge2_fmeasure_stderr": 0.000824659834492331, "rouge2_precision": 0.02442996212535727, "rouge2_precision_stderr": 0.0007519260848068276, "rouge2_recall": 0.042424873953699184, "rouge2_recall_stderr": 0.0013993567734203126, "rougeL_fmeasure": 0.11668679312793952, "rougeL_fmeasure_stderr": 0.001279584145980854, "rougeL_precision": 0.10658397240465457, "rougeL_precision_stderr": 0.0013324023033187138, "rougeL_recall": 0.1684211774861765, "rougeL_recall_stderr": 0.0022097636904149756, "rougeLsum_fmeasure": 0.1482203100115215, "rougeLsum_fmeasure_stderr": 0.0017644287180480047, "rougeLsum_precision": 0.1356637096139804, "rougeLsum_precision_stderr": 0.001799350424574685, "rougeLsum_recall": 0.20992335195224027, "rougeLsum_recall_stderr": 0.0027445156356427094}, "rephrase_en": {"bleu": 0.3628903862281783, "bleu_stderr": 0.040600834550736854, "rouge1_fmeasure": 0.10072739595349496, "rouge1_fmeasure_stderr": 0.0011867245098453186, "rouge1_precision": 0.11467425239533192, "rouge1_precision_stderr": 0.0015225012916013473, "rouge1_recall": 0.11441629521647928, "rouge1_recall_stderr": 0.0015727059489721053, "rouge2_fmeasure": 0.004828784168441771, "rouge2_fmeasure_stderr": 0.0002759061972464504, "rouge2_precision": 0.005508580331675803, "rouge2_precision_stderr": 0.00035383861846697813, "rouge2_recall": 0.005934869967984835, "rouge2_recall_stderr": 0.0004322756043539301, "rougeL_fmeasure": 0.07966550478447607, "rougeL_fmeasure_stderr": 0.0008671984140603575, "rougeL_precision": 0.09149413336589454, "rougeL_precision_stderr": 0.0011975294685730132, "rougeL_recall": 0.09135200468914431, "rougeL_recall_stderr": 0.0012290284607197216, "rougeLsum_fmeasure": 0.09709883418158977, "rougeLsum_fmeasure_stderr": 0.0011361943688270538, "rougeLsum_precision": 0.11056182525730968, "rougeLsum_precision_stderr": 0.0014655410176995765, "rougeLsum_recall": 0.11035544182626898, "rougeLsum_recall_stderr": 0.0015086333978719083}, "summarize_above_en": {"bleu": 0.4379392770159711, "bleu_stderr": 0.059428018607743945, "rouge1_fmeasure": 0.10225814979631906, "rouge1_fmeasure_stderr": 0.0012292507820030408, "rouge1_precision": 0.1163150797172004, "rouge1_precision_stderr": 0.0015925911586497405, "rouge1_recall": 0.11665631687345931, "rouge1_recall_stderr": 0.0016340035824879626, "rouge2_fmeasure": 0.005602755335977656, "rouge2_fmeasure_stderr": 0.000365207226287633, "rouge2_precision": 0.006595299157223728, "rouge2_precision_stderr": 0.0005108250821972147, "rouge2_recall": 0.006811278906280594, "rouge2_recall_stderr": 0.0005095210834151304, "rougeL_fmeasure": 0.08152225050163284, "rougeL_fmeasure_stderr": 0.0009069898459798317, "rougeL_precision": 0.09346370560850872, "rougeL_precision_stderr": 0.0012527414348738914, "rougeL_recall": 0.09379022195144442, "rougeL_recall_stderr": 0.0012826081895714718, "rougeLsum_fmeasure": 0.09858585234149649, "rougeLsum_fmeasure_stderr": 0.001170030683997042, "rougeLsum_precision": 0.11220025027683658, "rougeLsum_precision_stderr": 0.0015289183398502308, "rougeLsum_recall": 0.11254662956683745, "rougeLsum_recall_stderr": 0.0015531537080274286}, "tldr_en": {"bleu": 1.0367136986637764, "bleu_stderr": 0.10294385360100548, "rouge1_fmeasure": 0.11933695488013622, "rouge1_fmeasure_stderr": 0.001559164548856994, "rouge1_precision": 0.14110589305024318, "rouge1_precision_stderr": 0.0022270422789620343, "rouge1_recall": 0.1403877205314885, "rouge1_recall_stderr": 0.002190793145077092, "rouge2_fmeasure": 0.013472946625192286, "rouge2_fmeasure_stderr": 0.0005971595008055532, "rouge2_precision": 0.016440629225865595, "rouge2_precision_stderr": 0.0008773719234169698, "rouge2_recall": 0.01682561907914257, "rouge2_recall_stderr": 0.0008426407227716545, "rougeL_fmeasure": 0.09470570644133551, "rougeL_fmeasure_stderr": 0.0011669855247486087, "rougeL_precision": 0.11303183510467564, "rougeL_precision_stderr": 0.0017832927124786565, "rougeL_recall": 0.11265616862637728, "rougeL_recall_stderr": 0.0017655005819091217, "rougeLsum_fmeasure": 0.11342531741430635, "rougeLsum_fmeasure_stderr": 0.0014614019347966196, "rougeLsum_precision": 0.13426932254715146, "rougeLsum_precision_stderr": 0.0021052543187055337, "rougeLsum_recall": 0.13349014172459456, "rougeLsum_recall_stderr": 0.002067397596426611}, "write_abstract_en": {"bleu": 0.6359039546247384, "bleu_stderr": 0.05332890289165686, "rouge1_fmeasure": 0.11408900626000608, "rouge1_fmeasure_stderr": 0.0014182183684096998, "rouge1_precision": 0.11791706075978581, "rouge1_precision_stderr": 0.0015994717296165192, "rouge1_recall": 0.14298806278491627, "rouge1_recall_stderr": 0.0020625427368130608, "rouge2_fmeasure": 0.008686912843235644, "rouge2_fmeasure_stderr": 0.00045294754346949324, "rouge2_precision": 0.008285813515207935, "rouge2_precision_stderr": 0.0004549347251757663, "rouge2_recall": 0.012254279196802272, "rouge2_recall_stderr": 0.0007733247902712675, "rougeL_fmeasure": 0.0867863689660142, "rougeL_fmeasure_stderr": 0.0009676979999670107, "rougeL_precision": 0.09043062219460844, "rougeL_precision_stderr": 0.0011743927829203635, "rougeL_recall": 0.10998900310161605, "rougeL_recall_stderr": 0.0015428002199032057, "rougeLsum_fmeasure": 0.1085601417082136, "rougeLsum_fmeasure_stderr": 0.0013181344740805481, "rougeLsum_precision": 0.11235660105208539, "rougeLsum_precision_stderr": 0.001507091449296961, "rougeLsum_recall": 0.1359188111061881, "rougeLsum_recall_stderr": 0.0019151506035573415}}, "3": {"article_summary_en": {"bleu": 1.4186659295702861, "bleu_stderr": 0.050267910728881454, "rouge1_fmeasure": 0.12879034116675933, "rouge1_fmeasure_stderr": 0.002014213748068574, "rouge1_precision": 0.12488990987685827, "rouge1_precision_stderr": 0.0022261432116102544, "rouge1_recall": 0.18139575994673116, "rouge1_recall_stderr": 0.0030867748398314713, "rouge2_fmeasure": 0.02198351222980969, "rouge2_fmeasure_stderr": 0.0007661410803321813, "rouge2_precision": 0.020587304073537236, "rouge2_precision_stderr": 0.0008430364325238309, "rouge2_recall": 0.03345951804642443, "rouge2_recall_stderr": 0.0013102881750652396, "rougeL_fmeasure": 0.09609151005725931, "rougeL_fmeasure_stderr": 0.0014143522793016892, "rougeL_precision": 0.09378166940289302, "rougeL_precision_stderr": 0.0016774718846480157, "rougeL_recall": 0.1378319099477178, "rougeL_recall_stderr": 0.002341101765656631, "rougeLsum_fmeasure": 0.1195876958441179, "rougeLsum_fmeasure_stderr": 0.0018550103716636955, "rougeLsum_precision": 0.116314348038094, "rougeLsum_precision_stderr": 0.0020844285519718204, "rougeLsum_recall": 0.16840969828764962, "rougeLsum_recall_stderr": 0.0028496816197026674}, "rephrase_en": {"bleu": 0.3640822400959341, "bleu_stderr": 0.04928248150151389, "rouge1_fmeasure": 0.08360995103143794, "rouge1_fmeasure_stderr": 0.0013441180625539642, "rouge1_precision": 0.09881225588094651, "rouge1_precision_stderr": 0.0017794429029784138, "rouge1_recall": 0.0961080094935916, "rouge1_recall_stderr": 0.001760024204009069, "rouge2_fmeasure": 0.00494689889012699, "rouge2_fmeasure_stderr": 0.00032931853157837956, "rouge2_precision": 0.0059206327308198945, "rouge2_precision_stderr": 0.0004468897050553651, "rouge2_recall": 0.005917242814787239, "rouge2_recall_stderr": 0.00045428975938505313, "rougeL_fmeasure": 0.06662277406174887, "rougeL_fmeasure_stderr": 0.0010213036544403373, "rougeL_precision": 0.07953381242832525, "rougeL_precision_stderr": 0.001428896234358919, "rougeL_recall": 0.07718976821843865, "rougeL_recall_stderr": 0.0013856069309638303, "rougeLsum_fmeasure": 0.08045562840916225, "rougeLsum_fmeasure_stderr": 0.0012855845245021166, "rougeLsum_precision": 0.09515792843426966, "rougeLsum_precision_stderr": 0.001709487622838808, "rougeLsum_recall": 0.09256568091207279, "rougeLsum_recall_stderr": 0.0016852915566244572}, "summarize_above_en": {"bleu": 0.5442256675776663, "bleu_stderr": 0.037604550641844786, "rouge1_fmeasure": 0.08654940806312904, "rouge1_fmeasure_stderr": 0.001431495451108354, "rouge1_precision": 0.10060948026044556, "rouge1_precision_stderr": 0.0018664954448892226, "rouge1_recall": 0.10197302779012452, "rouge1_recall_stderr": 0.0019812796311759295, "rouge2_fmeasure": 0.0065193989842291565, "rouge2_fmeasure_stderr": 0.00042504340054855125, "rouge2_precision": 0.007376831208587836, "rouge2_precision_stderr": 0.0005437291438342406, "rouge2_recall": 0.008673705432290764, "rouge2_recall_stderr": 0.0007007938800809519, "rougeL_fmeasure": 0.06915495549341871, "rougeL_fmeasure_stderr": 0.0010949721512951217, "rougeL_precision": 0.08088970368544203, "rougeL_precision_stderr": 0.0014724520083722664, "rougeL_recall": 0.08233682962107754, "rougeL_recall_stderr": 0.0015887611692809386, "rougeLsum_fmeasure": 0.082797340411407, "rougeLsum_fmeasure_stderr": 0.001354438253975997, "rougeLsum_precision": 0.09635575140755301, "rougeLsum_precision_stderr": 0.0017746806567606403, "rougeLsum_recall": 0.09756525164753817, "rougeLsum_recall_stderr": 0.001879769069025684}, "tldr_en": {"bleu": 1.0055082276927305, "bleu_stderr": 0.07192737514794537, "rouge1_fmeasure": 0.10845969305714753, "rouge1_fmeasure_stderr": 0.001764500717605624, "rouge1_precision": 0.1432248072165103, "rouge1_precision_stderr": 0.0028194048557081534, "rouge1_recall": 0.1235766277421485, "rouge1_recall_stderr": 0.002354909584881938, "rouge2_fmeasure": 0.015547635018168346, "rouge2_fmeasure_stderr": 0.0006704388234796883, "rouge2_precision": 0.02165017024117859, "rouge2_precision_stderr": 0.0011383917848863225, "rouge2_recall": 0.018904933463519274, "rouge2_recall_stderr": 0.0009796659633542278, "rougeL_fmeasure": 0.08660256700931251, "rougeL_fmeasure_stderr": 0.001347993958631469, "rougeL_precision": 0.115448783961469, "rougeL_precision_stderr": 0.0023052494207092614, "rougeL_recall": 0.09991818086293902, "rougeL_recall_stderr": 0.0018968351003013303, "rougeLsum_fmeasure": 0.10174661203721236, "rougeLsum_fmeasure_stderr": 0.0016381663427203297, "rougeLsum_precision": 0.1347230613061051, "rougeLsum_precision_stderr": 0.002655304240899613, "rougeLsum_recall": 0.11587053571503414, "rougeLsum_recall_stderr": 0.0021893808381981995}, "write_abstract_en": {"bleu": 0.5690290357096291, "bleu_stderr": 0.08303885182927963, "rouge1_fmeasure": 0.0863434945247995, "rouge1_fmeasure_stderr": 0.0015282100730080173, "rouge1_precision": 0.09005735863253914, "rouge1_precision_stderr": 0.0017410925572476383, "rouge1_recall": 0.11209657560256954, "rouge1_recall_stderr": 0.002246234879953545, "rouge2_fmeasure": 0.007238486310418053, "rouge2_fmeasure_stderr": 0.00042895291336820845, "rouge2_precision": 0.006965462874923481, "rouge2_precision_stderr": 0.0004357269928233993, "rouge2_recall": 0.01068806664642742, "rouge2_recall_stderr": 0.0007581392108308288, "rougeL_fmeasure": 0.06590039763154197, "rougeL_fmeasure_stderr": 0.0010964007554027833, "rougeL_precision": 0.06963288035102946, "rougeL_precision_stderr": 0.0013235845589289316, "rougeL_recall": 0.08642316047519256, "rougeL_recall_stderr": 0.0017071161351831217, "rougeLsum_fmeasure": 0.08200533326129804, "rougeLsum_fmeasure_stderr": 0.0014384128001919997, "rougeLsum_precision": 0.08570933352018638, "rougeLsum_precision_stderr": 0.001644764365928756, "rougeLsum_recall": 0.10632118573218488, "rougeLsum_recall_stderr": 0.002114071365640021}}, "4": {"article_summary_en": {"bleu": 0.18764755097372476, "bleu_stderr": 0.0204323879125267, "rouge1_fmeasure": 0.04085144274673853, "rouge1_fmeasure_stderr": 0.001538442204027294, "rouge1_precision": 0.04274798462927153, "rouge1_precision_stderr": 0.0018161718038238448, "rouge1_recall": 0.05867994619730172, "rouge1_recall_stderr": 0.002374781099841643, "rouge2_fmeasure": 0.0071615346459846605, "rouge2_fmeasure_stderr": 0.0004694288024279032, "rouge2_precision": 0.006984195242455265, "rouge2_precision_stderr": 0.000603809740571673, "rouge2_recall": 0.011817282399442079, "rouge2_recall_stderr": 0.0009217929633034777, "rougeL_fmeasure": 0.031403237162404916, "rougeL_fmeasure_stderr": 0.0011428460910517797, "rougeL_precision": 0.0331311683624868, "rougeL_precision_stderr": 0.001416652850979173, "rougeL_recall": 0.04606968779468327, "rougeL_recall_stderr": 0.0018746567174795128, "rougeLsum_fmeasure": 0.03803522378880029, "rougeLsum_fmeasure_stderr": 0.0014259840855105786, "rougeLsum_precision": 0.039597785262755085, "rougeLsum_precision_stderr": 0.0016586096902770702, "rougeLsum_recall": 0.05473786135131624, "rougeLsum_recall_stderr": 0.0022121499800027366}, "rephrase_en": {"bleu": 0.022070239323623318, "bleu_stderr": 0.009020956658967978, "rouge1_fmeasure": 0.02596269332900368, "rouge1_fmeasure_stderr": 0.0010634101020032597, "rouge1_precision": 0.0317245796662674, "rouge1_precision_stderr": 0.0013705699322416266, "rouge1_recall": 0.03146018864612653, "rouge1_recall_stderr": 0.0014391156321984263, "rouge2_fmeasure": 0.0019833072972918566, "rouge2_fmeasure_stderr": 0.0002144425508793813, "rouge2_precision": 0.002339551167089779, "rouge2_precision_stderr": 0.00030256564830245586, "rouge2_recall": 0.003101162831484645, "rouge2_recall_stderr": 0.0004679085866658427, "rougeL_fmeasure": 0.020998319543683103, "rougeL_fmeasure_stderr": 0.0008262281758861216, "rougeL_precision": 0.026049745321603573, "rougeL_precision_stderr": 0.0011243334623461175, "rougeL_recall": 0.025594964978776304, "rougeL_recall_stderr": 0.0011360606064423507, "rougeLsum_fmeasure": 0.02460219706818639, "rougeLsum_fmeasure_stderr": 0.0009968526836547482, "rougeLsum_precision": 0.03023574490650669, "rougeLsum_precision_stderr": 0.0013013309198418228, "rougeLsum_recall": 0.029726826443738044, "rougeLsum_recall_stderr": 0.0013382698786662225}, "summarize_above_en": {"bleu": 0.027510143284592198, "bleu_stderr": 0.005850102428249243, "rouge1_fmeasure": 0.02705120556648003, "rouge1_fmeasure_stderr": 0.001128461395321214, "rouge1_precision": 0.03285278805076312, "rouge1_precision_stderr": 0.00151492862638139, "rouge1_recall": 0.033499707980673206, "rouge1_recall_stderr": 0.0015787383836412087, "rouge2_fmeasure": 0.0026853344180586664, "rouge2_fmeasure_stderr": 0.0002789624736107807, "rouge2_precision": 0.003253495732258925, "rouge2_precision_stderr": 0.00040392310255452183, "rouge2_recall": 0.004071265417854878, "rouge2_recall_stderr": 0.0005813660435076962, "rougeL_fmeasure": 0.022141442290806702, "rougeL_fmeasure_stderr": 0.0008958829005211576, "rougeL_precision": 0.027230939273538826, "rougeL_precision_stderr": 0.001255620650530008, "rougeL_recall": 0.02759081624466607, "rougeL_recall_stderr": 0.0012884449077523894, "rougeLsum_fmeasure": 0.02576886539837896, "rougeLsum_fmeasure_stderr": 0.0010599565782314143, "rougeLsum_precision": 0.031233183019105354, "rougeLsum_precision_stderr": 0.0014213211972707832, "rougeLsum_recall": 0.0319845426682248, "rougeLsum_recall_stderr": 0.001491847145002001}, "tldr_en": {"bleu": 0.0464769949251449, "bleu_stderr": 0.005281612141215288, "rouge1_fmeasure": 0.03803967268390006, "rouge1_fmeasure_stderr": 0.0014747568915058733, "rouge1_precision": 0.05608048532310048, "rouge1_precision_stderr": 0.002435498849231569, "rouge1_recall": 0.041593600839943914, "rouge1_recall_stderr": 0.001788014682833587, "rouge2_fmeasure": 0.006755300956624583, "rouge2_fmeasure_stderr": 0.0005462948561714105, "rouge2_precision": 0.011745234816576059, "rouge2_precision_stderr": 0.0010829411163804264, "rouge2_recall": 0.007380582194532306, "rouge2_recall_stderr": 0.0007127969246877938, "rougeL_fmeasure": 0.031443909785773674, "rougeL_fmeasure_stderr": 0.0012099672207623704, "rougeL_precision": 0.047091703984391005, "rougeL_precision_stderr": 0.002065424301205954, "rougeL_recall": 0.034604035967383255, "rougeL_recall_stderr": 0.0014944258543141873, "rougeLsum_fmeasure": 0.03593453392452451, "rougeLsum_fmeasure_stderr": 0.0013935406055845413, "rougeLsum_precision": 0.05323231626482197, "rougeLsum_precision_stderr": 0.0023275252393686156, "rougeLsum_recall": 0.0391023340007786, "rougeLsum_recall_stderr": 0.0016636743475211388}, "write_abstract_en": {"bleu": 0.016816379280954568, "bleu_stderr": 0.0028919321680318318, "rouge1_fmeasure": 0.021738632248596658, "rouge1_fmeasure_stderr": 0.0010230448733526455, "rouge1_precision": 0.02299224348433701, "rouge1_precision_stderr": 0.0011412033083596786, "rouge1_recall": 0.030086106435386208, "rouge1_recall_stderr": 0.001556085408646244, "rouge2_fmeasure": 0.001875948079941924, "rouge2_fmeasure_stderr": 0.000219572547682823, "rouge2_precision": 0.0017495363473227336, "rouge2_precision_stderr": 0.00020151602411722723, "rouge2_recall": 0.0032970556699345034, "rouge2_recall_stderr": 0.0004918025374367564, "rougeL_fmeasure": 0.01708346323437329, "rougeL_fmeasure_stderr": 0.0007728353496458206, "rougeL_precision": 0.01828959837223259, "rougeL_precision_stderr": 0.0009017986426573455, "rougeL_recall": 0.024055207310948443, "rougeL_recall_stderr": 0.0012481605588282325, "rougeLsum_fmeasure": 0.02048581320979614, "rougeLsum_fmeasure_stderr": 0.0009585758119225723, "rougeLsum_precision": 0.021695271758735132, "rougeLsum_precision_stderr": 0.0010708297762772132, "rougeLsum_recall": 0.028324718060384762, "rougeLsum_recall_stderr": 0.001443357150753234}}, "5": {"article_summary_en": {"bleu": 1.2081769471696679e-09, "bleu_stderr": 4.7758554492272945e-09, "rouge1_fmeasure": 0.005950641245994375, "rouge1_fmeasure_stderr": 0.0006411674676836966, "rouge1_precision": 0.006928543414105365, "rouge1_precision_stderr": 0.0008521915511742353, "rouge1_recall": 0.00867185146550297, "rouge1_recall_stderr": 0.0010332808843393272, "rouge2_fmeasure": 0.0011656375598739542, "rouge2_fmeasure_stderr": 0.0002028046057963131, "rouge2_precision": 0.001396425548191038, "rouge2_precision_stderr": 0.0003008386819272615, "rouge2_recall": 0.0020329927104609604, "rouge2_recall_stderr": 0.00048577777702315096, "rougeL_fmeasure": 0.0046037610582904, "rougeL_fmeasure_stderr": 0.0004842752495293122, "rougeL_precision": 0.005494500329872309, "rougeL_precision_stderr": 0.0007044489282665799, "rougeL_recall": 0.006910731196408219, "rougeL_recall_stderr": 0.0008474442564134671, "rougeLsum_fmeasure": 0.0055130820845512825, "rougeLsum_fmeasure_stderr": 0.0005938752458158761, "rougeLsum_precision": 0.006515436893618955, "rougeLsum_precision_stderr": 0.0008141521585116435, "rougeLsum_recall": 0.008010452744131268, "rougeLsum_recall_stderr": 0.0009551600048254268}, "rephrase_en": {"bleu": 1.2772835382495755e-13, "bleu_stderr": 3.981569081927512e-12, "rouge1_fmeasure": 0.004061499208353005, "rouge1_fmeasure_stderr": 0.00046516835238848473, "rouge1_precision": 0.004997411592452321, "rouge1_precision_stderr": 0.0005839652233329812, "rouge1_recall": 0.00516993867487459, "rouge1_recall_stderr": 0.0007131741906943778, "rouge2_fmeasure": 0.0002762510614131578, "rouge2_fmeasure_stderr": 7.152448161217703e-05, "rouge2_precision": 0.00030964206877279654, "rouge2_precision_stderr": 8.927954397265049e-05, "rouge2_recall": 0.0005971005703343351, "rouge2_recall_stderr": 0.00021977639166152163, "rougeL_fmeasure": 0.003257613603154482, "rougeL_fmeasure_stderr": 0.0003601612804489262, "rougeL_precision": 0.004026290704976211, "rougeL_precision_stderr": 0.00046120664542663453, "rougeL_recall": 0.0042081128532273256, "rougeL_recall_stderr": 0.0005776147810982953, "rougeLsum_fmeasure": 0.0038410375028680617, "rougeLsum_fmeasure_stderr": 0.00043981063385292154, "rougeLsum_precision": 0.004781410549830059, "rougeLsum_precision_stderr": 0.0005638818969053312, "rougeLsum_recall": 0.004893422518392296, "rougeLsum_recall_stderr": 0.0006832059638435896}, "summarize_above_en": {"bleu": 3.9529978759982985e-15, "bleu_stderr": 1.548319477203052e-13, "rouge1_fmeasure": 0.004055948100688518, "rouge1_fmeasure_stderr": 0.00047821717141908343, "rouge1_precision": 0.005131645813217702, "rouge1_precision_stderr": 0.0006494612556736446, "rouge1_recall": 0.0046603087139718904, "rouge1_recall_stderr": 0.0005994833560269134, "rouge2_fmeasure": 0.00042158314099139017, "rouge2_fmeasure_stderr": 0.00010671999988396933, "rouge2_precision": 0.0006565696469248757, "rouge2_precision_stderr": 0.00021376994443478634, "rouge2_recall": 0.00046749083156390686, "rouge2_recall_stderr": 0.00012176761634464935, "rougeL_fmeasure": 0.003372046824276411, "rougeL_fmeasure_stderr": 0.00038942868804587514, "rougeL_precision": 0.004234119839442783, "rougeL_precision_stderr": 0.0005284078757495208, "rougeL_recall": 0.00396076135348473, "rougeL_recall_stderr": 0.0005103337395972377, "rougeLsum_fmeasure": 0.0039257863548093274, "rougeLsum_fmeasure_stderr": 0.00046232884670699545, "rougeLsum_precision": 0.004974502856539407, "rougeLsum_precision_stderr": 0.0006280274207578934, "rougeLsum_recall": 0.004513499194743017, "rougeLsum_recall_stderr": 0.0005832210379541333}, "tldr_en": {"bleu": 7.71421931319727e-14, "bleu_stderr": 4.575898076497286e-13, "rouge1_fmeasure": 0.006408772411533697, "rouge1_fmeasure_stderr": 0.0006726664225328778, "rouge1_precision": 0.009319821178210992, "rouge1_precision_stderr": 0.0010269796471685194, "rouge1_recall": 0.007261443669465562, "rouge1_recall_stderr": 0.0009201674527650682, "rouge2_fmeasure": 0.001215199948152673, "rouge2_fmeasure_stderr": 0.00024366601487357684, "rouge2_precision": 0.0015883326473273408, "rouge2_precision_stderr": 0.0003471561820758166, "rouge2_recall": 0.0016746964377212603, "rouge2_recall_stderr": 0.00043827050828643875, "rougeL_fmeasure": 0.005446190005924919, "rougeL_fmeasure_stderr": 0.0005737856458351668, "rougeL_precision": 0.007922705066461089, "rougeL_precision_stderr": 0.0008728161809959782, "rougeL_recall": 0.006196890284199744, "rougeL_recall_stderr": 0.000796669253101562, "rougeLsum_fmeasure": 0.006002979726182862, "rougeLsum_fmeasure_stderr": 0.0006246362092905004, "rougeLsum_precision": 0.008783315274046653, "rougeLsum_precision_stderr": 0.0009687512562761863, "rougeLsum_recall": 0.006837799638085168, "rougeLsum_recall_stderr": 0.0008734893361383668}, "write_abstract_en": {"bleu": 1.1597815660645416e-20, "bleu_stderr": 6.856426087822371e-20, "rouge1_fmeasure": 0.0023847991624654733, "rouge1_fmeasure_stderr": 0.000384610434523063, "rouge1_precision": 0.0023192080637707735, "rouge1_precision_stderr": 0.00038854174236947536, "rouge1_recall": 0.0037156411516436165, "rouge1_recall_stderr": 0.0006659054396004237, "rouge2_fmeasure": 0.0003122235342379389, "rouge2_fmeasure_stderr": 9.229879998061021e-05, "rouge2_precision": 0.00024483684853279374, "rouge2_precision_stderr": 7.040995395638042e-05, "rouge2_recall": 0.0005891611955524744, "rouge2_recall_stderr": 0.00018205158176419917, "rougeL_fmeasure": 0.001821148625234418, "rougeL_fmeasure_stderr": 0.0002799930215985291, "rougeL_precision": 0.0018119271192860117, "rougeL_precision_stderr": 0.0002971679095161747, "rougeL_recall": 0.0028628954473527285, "rougeL_recall_stderr": 0.0005077613704836201, "rougeLsum_fmeasure": 0.0022835778404728443, "rougeLsum_fmeasure_stderr": 0.00036781738986975464, "rougeLsum_precision": 0.002232415013733976, "rougeLsum_precision_stderr": 0.000374058105161406, "rougeLsum_recall": 0.0035504517322428614, "rougeLsum_recall_stderr": 0.0006368246151758458}}}, "anli_r1": {"0": {"GPT-3 style": {"acc": 0.329, "acc_norm": 0.333, "acc_norm_stderr": 0.014910846164229856, "acc_stderr": 0.014865395385928376, "subset": 1}, "MNLI crowdsource": {"acc": 0.331, "acc_norm": 0.32, "acc_norm_stderr": 0.01475865230357488, "acc_stderr": 0.01488827258820393, "subset": 1}, "can we infer": {"acc": 0.336, "acc_norm": 0.346, "acc_norm_stderr": 0.015050266127564438, "acc_stderr": 0.014944140233795027, "subset": 1}, "guaranteed/possible/impossible": {"acc": 0.324, "acc_norm": 0.332, "acc_norm_stderr": 0.014899597242811475, "acc_stderr": 0.014806864733738863, "subset": 1}, "justified in saying": {"acc": 0.333, "acc_norm": 0.355, "acc_norm_stderr": 0.01513949154378053, "acc_stderr": 0.014910846164229875, "subset": 1}}, "1": {"GPT-3 style": {"acc": 0.334, "acc_norm": 0.328, "acc_norm_stderr": 0.014853842487270334, "acc_stderr": 0.01492201952373296, "subset": 1}, "MNLI crowdsource": {"acc": 0.333, "acc_norm": 0.333, "acc_norm_stderr": 0.014910846164229863, "acc_stderr": 0.014910846164229863, "subset": 1}, "can we infer": {"acc": 0.331, "acc_norm": 0.338, "acc_norm_stderr": 0.01496596071022448, "acc_stderr": 0.014888272588203933, "subset": 1}, "guaranteed/possible/impossible": {"acc": 0.333, "acc_norm": 0.333, "acc_norm_stderr": 0.014910846164229863, "acc_stderr": 0.014910846164229863, "subset": 1}, "justified in saying": {"acc": 0.332, "acc_norm": 0.336, "acc_norm_stderr": 0.014944140233795023, "acc_stderr": 0.014899597242811485, "subset": 1}}, "2": {"GPT-3 style": {"acc": 0.363, "acc_norm": 0.354, "acc_norm_stderr": 0.015129868238451772, "acc_stderr": 0.015213890444671288, "subset": 1}, "MNLI crowdsource": {"acc": 0.339, "acc_norm": 0.333, "acc_norm_stderr": 0.014910846164229864, "acc_stderr": 0.01497675877162034, "subset": 1}, "can we infer": {"acc": 0.353, "acc_norm": 0.354, "acc_norm_stderr": 0.015129868238451772, "acc_stderr": 0.0151201726054837, "subset": 1}, "guaranteed/possible/impossible": {"acc": 0.348, "acc_norm": 0.348, "acc_norm_stderr": 0.01507060460376841, "acc_stderr": 0.01507060460376841, "subset": 1}, "justified in saying": {"acc": 0.353, "acc_norm": 0.354, "acc_norm_stderr": 0.015129868238451772, "acc_stderr": 0.015120172605483703, "subset": 1}}, "3": {"GPT-3 style": {"acc": 0.355, "acc_norm": 0.339, "acc_norm_stderr": 0.014976758771620335, "acc_stderr": 0.015139491543780529, "subset": 1}, "MNLI crowdsource": {"acc": 0.329, "acc_norm": 0.332, "acc_norm_stderr": 0.014899597242811485, "acc_stderr": 0.014865395385928367, "subset": 1}, "can we infer": {"acc": 0.35, "acc_norm": 0.335, "acc_norm_stderr": 0.014933117490932575, "acc_stderr": 0.015090650341444236, "subset": 1}, "guaranteed/possible/impossible": {"acc": 0.35, "acc_norm": 0.35, "acc_norm_stderr": 0.015090650341444233, "acc_stderr": 0.015090650341444233, "subset": 1}, "justified in saying": {"acc": 0.346, "acc_norm": 0.331, "acc_norm_stderr": 0.014888272588203931, "acc_stderr": 0.015050266127564433, "subset": 1}}, "4": {"GPT-3 style": {"acc": 0.348, "acc_norm": 0.354, "acc_norm_stderr": 0.015129868238451773, "acc_stderr": 0.01507060460376841, "subset": 1}, "MNLI crowdsource": {"acc": 0.327, "acc_norm": 0.325, "acc_norm_stderr": 0.014818724459095524, "acc_stderr": 0.014842213153411244, "subset": 1}, "can we infer": {"acc": 0.335, "acc_norm": 0.344, "acc_norm_stderr": 0.015029633724408947, "acc_stderr": 0.014933117490932577, "subset": 1}, "guaranteed/possible/impossible": {"acc": 0.325, "acc_norm": 0.335, "acc_norm_stderr": 0.014933117490932579, "acc_stderr": 0.014818724459095522, "subset": 1}, "justified in saying": {"acc": 0.345, "acc_norm": 0.355, "acc_norm_stderr": 0.01513949154378053, "acc_stderr": 0.015039986742055235, "subset": 1}}, "5": {"GPT-3 style": {"acc": 0.352, "acc_norm": 0.355, "acc_norm_stderr": 0.015139491543780529, "acc_stderr": 0.015110404505648658, "subset": 1}, "MNLI crowdsource": {"acc": 0.308, "acc_norm": 0.302, "acc_norm_stderr": 0.01452608023545955, "acc_stderr": 0.014606483127342763, "subset": 1}, "can we infer": {"acc": 0.342, "acc_norm": 0.334, "acc_norm_stderr": 0.014922019523732958, "acc_stderr": 0.015008706182121728, "subset": 1}, "guaranteed/possible/impossible": {"acc": 0.328, "acc_norm": 0.327, "acc_norm_stderr": 0.01484221315341124, "acc_stderr": 0.014853842487270334, "subset": 1}, "justified in saying": {"acc": 0.344, "acc_norm": 0.343, "acc_norm_stderr": 0.015019206922356953, "acc_stderr": 0.015029633724408947, "subset": 1}}}, "anli_r2": {"0": {"GPT-3 style": {"acc": 0.32, "acc_norm": 0.342, "acc_norm_stderr": 0.015008706182121734, "acc_stderr": 0.01475865230357489, "subset": 2}, "MNLI crowdsource": {"acc": 0.339, "acc_norm": 0.323, "acc_norm_stderr": 0.014794927843348642, "acc_stderr": 0.014976758771620342, "subset": 2}, "can we infer": {"acc": 0.33, "acc_norm": 0.336, "acc_norm_stderr": 0.014944140233795023, "acc_stderr": 0.014876872027456729, "subset": 2}, "guaranteed/possible/impossible": {"acc": 0.334, "acc_norm": 0.332, "acc_norm_stderr": 0.01489959724281147, "acc_stderr": 0.01492201952373296, "subset": 2}, "justified in saying": {"acc": 0.333, "acc_norm": 0.338, "acc_norm_stderr": 0.01496596071022447, "acc_stderr": 0.014910846164229873, "subset": 2}}, "1": {"GPT-3 style": {"acc": 0.321, "acc_norm": 0.315, "acc_norm_stderr": 0.014696631960792506, "acc_stderr": 0.014770821817934647, "subset": 2}, "MNLI crowdsource": {"acc": 0.315, "acc_norm": 0.315, "acc_norm_stderr": 0.014696631960792506, "acc_stderr": 0.014696631960792506, "subset": 2}, "can we infer": {"acc": 0.325, "acc_norm": 0.32, "acc_norm_stderr": 0.014758652303574886, "acc_stderr": 0.014818724459095524, "subset": 2}, "guaranteed/possible/impossible": {"acc": 0.315, "acc_norm": 0.315, "acc_norm_stderr": 0.014696631960792506, "acc_stderr": 0.014696631960792506, "subset": 2}, "justified in saying": {"acc": 0.324, "acc_norm": 0.321, "acc_norm_stderr": 0.014770821817934647, "acc_stderr": 0.01480686473373886, "subset": 2}}, "2": {"GPT-3 style": {"acc": 0.33, "acc_norm": 0.326, "acc_norm_stderr": 0.014830507204541028, "acc_stderr": 0.01487687202745673, "subset": 2}, "MNLI crowdsource": {"acc": 0.327, "acc_norm": 0.327, "acc_norm_stderr": 0.014842213153411237, "acc_stderr": 0.014842213153411237, "subset": 2}, "can we infer": {"acc": 0.326, "acc_norm": 0.333, "acc_norm_stderr": 0.014910846164229873, "acc_stderr": 0.014830507204541031, "subset": 2}, "guaranteed/possible/impossible": {"acc": 0.321, "acc_norm": 0.319, "acc_norm_stderr": 0.014746404865473477, "acc_stderr": 0.014770821817934649, "subset": 2}, "justified in saying": {"acc": 0.328, "acc_norm": 0.331, "acc_norm_stderr": 0.014888272588203928, "acc_stderr": 0.014853842487270334, "subset": 2}}, "3": {"GPT-3 style": {"acc": 0.321, "acc_norm": 0.329, "acc_norm_stderr": 0.014865395385928369, "acc_stderr": 0.014770821817934649, "subset": 2}, "MNLI crowdsource": {"acc": 0.329, "acc_norm": 0.327, "acc_norm_stderr": 0.014842213153411242, "acc_stderr": 0.014865395385928367, "subset": 2}, "can we infer": {"acc": 0.312, "acc_norm": 0.329, "acc_norm_stderr": 0.01486539538592837, "acc_stderr": 0.014658474370509014, "subset": 2}, "guaranteed/possible/impossible": {"acc": 0.296, "acc_norm": 0.297, "acc_norm_stderr": 0.0144568322948011, "acc_stderr": 0.01444273494157502, "subset": 2}, "justified in saying": {"acc": 0.318, "acc_norm": 0.318, "acc_norm_stderr": 0.014734079309311901, "acc_stderr": 0.014734079309311901, "subset": 2}}, "4": {"GPT-3 style": {"acc": 0.327, "acc_norm": 0.318, "acc_norm_stderr": 0.014734079309311901, "acc_stderr": 0.014842213153411239, "subset": 2}, "MNLI crowdsource": {"acc": 0.305, "acc_norm": 0.311, "acc_norm_stderr": 0.014645596385722692, "acc_stderr": 0.01456664639466438, "subset": 2}, "can we infer": {"acc": 0.316, "acc_norm": 0.318, "acc_norm_stderr": 0.014734079309311901, "acc_stderr": 0.014709193056057134, "subset": 2}, "guaranteed/possible/impossible": {"acc": 0.316, "acc_norm": 0.311, "acc_norm_stderr": 0.014645596385722694, "acc_stderr": 0.01470919305605712, "subset": 2}, "justified in saying": {"acc": 0.314, "acc_norm": 0.328, "acc_norm_stderr": 0.01485384248727033, "acc_stderr": 0.014683991951087978, "subset": 2}}, "5": {"GPT-3 style": {"acc": 0.337, "acc_norm": 0.329, "acc_norm_stderr": 0.014865395385928373, "acc_stderr": 0.014955087918653591, "subset": 2}, "MNLI crowdsource": {"acc": 0.313, "acc_norm": 0.317, "acc_norm_stderr": 0.014721675438880233, "acc_stderr": 0.014671272822977892, "subset": 2}, "can we infer": {"acc": 0.326, "acc_norm": 0.334, "acc_norm_stderr": 0.014922019523732954, "acc_stderr": 0.014830507204541033, "subset": 2}, "guaranteed/possible/impossible": {"acc": 0.325, "acc_norm": 0.328, "acc_norm_stderr": 0.014853842487270334, "acc_stderr": 0.014818724459095524, "subset": 2}, "justified in saying": {"acc": 0.329, "acc_norm": 0.338, "acc_norm_stderr": 0.014965960710224468, "acc_stderr": 0.014865395385928369, "subset": 2}}}, "anli_r3": {"0": {"GPT-3 style": {"acc": 0.30416666666666664, "acc_norm": 0.3416666666666667, "acc_norm_stderr": 0.013696658778002519, "acc_stderr": 0.013286140243317441, "subset": 3}, "MNLI crowdsource": {"acc": 0.3358333333333333, "acc_norm": 0.33416666666666667, "acc_norm_stderr": 0.01362243481313678, "acc_stderr": 0.013639261190932873, "subset": 3}, "can we infer": {"acc": 0.3233333333333333, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.013613950010225613, "acc_stderr": 0.013508372867300217, "subset": 3}, "guaranteed/possible/impossible": {"acc": 0.32916666666666666, "acc_norm": 0.33, "acc_norm_stderr": 0.013579531277800918, "acc_stderr": 0.013570806258433628, "subset": 3}, "justified in saying": {"acc": 0.33166666666666667, "acc_norm": 0.33416666666666667, "acc_norm_stderr": 0.01362243481313677, "acc_stderr": 0.013596836729485159, "subset": 3}}, "1": {"GPT-3 style": {"acc": 0.3433333333333333, "acc_norm": 0.3375, "acc_norm_stderr": 0.013655897185463657, "acc_stderr": 0.01371263383046586, "subset": 3}, "MNLI crowdsource": {"acc": 0.33666666666666667, "acc_norm": 0.33666666666666667, "acc_norm_stderr": 0.013647602942406393, "acc_stderr": 0.013647602942406393, "subset": 3}, "can we infer": {"acc": 0.345, "acc_norm": 0.3408333333333333, "acc_norm_stderr": 0.013688600793296934, "acc_stderr": 0.013728421539454876, "subset": 3}, "guaranteed/possible/impossible": {"acc": 0.33666666666666667, "acc_norm": 0.33666666666666667, "acc_norm_stderr": 0.013647602942406393, "acc_stderr": 0.013647602942406393, "subset": 3}, "justified in saying": {"acc": 0.355, "acc_norm": 0.33916666666666667, "acc_norm_stderr": 0.013672343491681819, "acc_stderr": 0.013819249004047296, "subset": 3}}, "2": {"GPT-3 style": {"acc": 0.335, "acc_norm": 0.3383333333333333, "acc_norm_stderr": 0.013664144006618261, "acc_stderr": 0.013630871843821465, "subset": 3}, "MNLI crowdsource": {"acc": 0.30833333333333335, "acc_norm": 0.3075, "acc_norm_stderr": 0.013326707242912048, "acc_stderr": 0.013336721143136469, "subset": 3}, "can we infer": {"acc": 0.3275, "acc_norm": 0.32666666666666666, "acc_norm_stderr": 0.013544340907003665, "acc_stderr": 0.013553211167251953, "subset": 3}, "guaranteed/possible/impossible": {"acc": 0.31333333333333335, "acc_norm": 0.31, "acc_norm_stderr": 0.01335659633120026, "acc_stderr": 0.013395739415639082, "subset": 3}, "justified in saying": {"acc": 0.33166666666666667, "acc_norm": 0.3233333333333333, "acc_norm_stderr": 0.01350837286730022, "acc_stderr": 0.01359683672948517, "subset": 3}}, "3": {"GPT-3 style": {"acc": 0.3541666666666667, "acc_norm": 0.35583333333333333, "acc_norm_stderr": 0.01382651874849331, "acc_stderr": 0.013811933499570954, "subset": 3}, "MNLI crowdsource": {"acc": 0.3308333333333333, "acc_norm": 0.32416666666666666, "acc_norm_stderr": 0.013517438120881636, "acc_stderr": 0.013588208070708999, "subset": 3}, "can we infer": {"acc": 0.3433333333333333, "acc_norm": 0.3525, "acc_norm_stderr": 0.01379716491891836, "acc_stderr": 0.01371263383046586, "subset": 3}, "guaranteed/possible/impossible": {"acc": 0.32, "acc_norm": 0.32, "acc_norm_stderr": 0.01347162092976914, "acc_stderr": 0.013471620929769142, "subset": 3}, "justified in saying": {"acc": 0.345, "acc_norm": 0.3541666666666667, "acc_norm_stderr": 0.013811933499570956, "acc_stderr": 0.013728421539454878, "subset": 3}}, "4": {"GPT-3 style": {"acc": 0.34833333333333333, "acc_norm": 0.32416666666666666, "acc_norm_stderr": 0.013517438120881617, "acc_stderr": 0.013759437498874072, "subset": 3}, "MNLI crowdsource": {"acc": 0.32916666666666666, "acc_norm": 0.3283333333333333, "acc_norm_stderr": 0.013562032919529019, "acc_stderr": 0.013570806258433628, "subset": 3}, "can we infer": {"acc": 0.3466666666666667, "acc_norm": 0.33916666666666667, "acc_norm_stderr": 0.013672343491681808, "acc_stderr": 0.013744022550571942, "subset": 3}, "guaranteed/possible/impossible": {"acc": 0.3175, "acc_norm": 0.31833333333333336, "acc_norm_stderr": 0.0134529489969963, "acc_stderr": 0.013443538681348052, "subset": 3}, "justified in saying": {"acc": 0.3408333333333333, "acc_norm": 0.33416666666666667, "acc_norm_stderr": 0.013622434813136765, "acc_stderr": 0.013688600793296939, "subset": 3}}, "5": {"GPT-3 style": {"acc": 0.32916666666666666, "acc_norm": 0.3225, "acc_norm_stderr": 0.013499258621103247, "acc_stderr": 0.013570806258433628, "subset": 3}, "MNLI crowdsource": {"acc": 0.29833333333333334, "acc_norm": 0.30833333333333335, "acc_norm_stderr": 0.013336721143136467, "acc_stderr": 0.013213160837301237, "subset": 3}, "can we infer": {"acc": 0.3308333333333333, "acc_norm": 0.3258333333333333, "acc_norm_stderr": 0.013535422043417466, "acc_stderr": 0.013588208070708992, "subset": 3}, "guaranteed/possible/impossible": {"acc": 0.31, "acc_norm": 0.31166666666666665, "acc_norm_stderr": 0.0133762687909821, "acc_stderr": 0.013356596331200258, "subset": 3}, "justified in saying": {"acc": 0.32666666666666666, "acc_norm": 0.3233333333333333, "acc_norm_stderr": 0.013508372867300231, "acc_stderr": 0.013544340907003663, "subset": 3}}}, "arc_easy": {"0": {"heres_a_problem": {"acc": 0.2175767918088737, "acc_norm": 0.2175767918088737, "acc_norm_stderr": 0.0120572620209725, "acc_stderr": 0.0120572620209725}, "i_am_hesitating": {"acc": 0.2158703071672355, "acc_norm": 0.2696245733788396, "acc_norm_stderr": 0.012968040686869157, "acc_stderr": 0.012022975360030675}, "multiple_choice": {"acc": 0.29124579124579125, "acc_norm": 0.2676767676767677, "acc_norm_stderr": 0.00908500014709935, "acc_stderr": 0.009322788837938871}, "pick_the_most_correct_option": {"acc": 0.22013651877133106, "acc_norm": 0.22013651877133106, "acc_norm_stderr": 0.012108124883460976, "acc_stderr": 0.012108124883460976}, "qa_options": {"acc": 0.20648464163822525, "acc_norm": 0.26109215017064846, "acc_norm_stderr": 0.012835523909473845, "acc_stderr": 0.011828865619002316}}, "1": {"heres_a_problem": {"acc": 0.23779461279461278, "acc_norm": 0.23779461279461278, "acc_norm_stderr": 0.008735850753507994, "acc_stderr": 0.008735850753507994}, "i_am_hesitating": {"acc": 0.2235494880546075, "acc_norm": 0.27303754266211605, "acc_norm_stderr": 0.01301933276263573, "acc_stderr": 0.012174896631202605}, "multiple_choice": {"acc": 0.22866894197952217, "acc_norm": 0.25426621160409557, "acc_norm_stderr": 0.012724999945157744, "acc_stderr": 0.01227285358254081}, "pick_the_most_correct_option": {"acc": 0.2398989898989899, "acc_norm": 0.2398989898989899, "acc_norm_stderr": 0.008762298774190588, "acc_stderr": 0.008762298774190588}, "qa_options": {"acc": 0.29503367003367004, "acc_norm": 0.28114478114478114, "acc_norm_stderr": 0.009224735470287005, "acc_stderr": 0.009358110551087425}}, "2": {"heres_a_problem": {"acc": 0.23208191126279865, "acc_norm": 0.23208191126279865, "acc_norm_stderr": 0.012336718284948854, "acc_stderr": 0.012336718284948854}, "i_am_hesitating": {"acc": 0.2167235494880546, "acc_norm": 0.26621160409556316, "acc_norm_stderr": 0.012915774781523216, "acc_stderr": 0.012040156713481189}, "multiple_choice": {"acc": 0.2895622895622896, "acc_norm": 0.28619528619528617, "acc_norm_stderr": 0.009274470774627732, "acc_stderr": 0.009306838912173909}, "pick_the_most_correct_option": {"acc": 0.2596801346801347, "acc_norm": 0.2596801346801347, "acc_norm_stderr": 0.008996990428562215, "acc_stderr": 0.008996990428562215}, "qa_options": {"acc": 0.2908249158249158, "acc_norm": 0.27441077441077444, "acc_norm_stderr": 0.009156177122244528, "acc_stderr": 0.009318815921176653}}, "3": {"heres_a_problem": {"acc": 0.25841750841750843, "acc_norm": 0.25841750841750843, "acc_norm_stderr": 0.008982741341291298, "acc_stderr": 0.008982741341291298}, "i_am_hesitating": {"acc": 0.2803030303030303, "acc_norm": 0.27314814814814814, "acc_norm_stderr": 0.009143032718360347, "acc_stderr": 0.009216306864088033}, "multiple_choice": {"acc": 0.27735690235690236, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.009369711585684304, "acc_stderr": 0.009186490105111902}, "pick_the_most_correct_option": {"acc": 0.2537878787878788, "acc_norm": 0.2537878787878788, "acc_norm_stderr": 0.00892965706580829, "acc_stderr": 0.00892965706580829}, "qa_options": {"acc": 0.2824074074074074, "acc_norm": 0.2756734006734007, "acc_norm_stderr": 0.009169229476542563, "acc_stderr": 0.009237303403479332}}, "4": {"heres_a_problem": {"acc": 0.24146757679180889, "acc_norm": 0.24146757679180889, "acc_norm_stderr": 0.012506564839739429, "acc_stderr": 0.012506564839739429}, "i_am_hesitating": {"acc": 0.23037542662116042, "acc_norm": 0.2713310580204778, "acc_norm_stderr": 0.012993807727545784, "acc_stderr": 0.01230492841874761}, "multiple_choice": {"acc": 0.2781986531986532, "acc_norm": 0.2845117845117845, "acc_norm_stderr": 0.00925805092561882, "acc_stderr": 0.009195059601583901}, "pick_the_most_correct_option": {"acc": 0.2542087542087542, "acc_norm": 0.2542087542087542, "acc_norm_stderr": 0.008934537681141544, "acc_stderr": 0.008934537681141544}, "qa_options": {"acc": 0.2150170648464164, "acc_norm": 0.2525597269624573, "acc_norm_stderr": 0.01269672898020771, "acc_stderr": 0.012005717634133616}}, "5": {"heres_a_problem": {"acc": 0.25715488215488214, "acc_norm": 0.25715488215488214, "acc_norm_stderr": 0.008968394768971991, "acc_stderr": 0.008968394768971991}, "i_am_hesitating": {"acc": 0.22610921501706485, "acc_norm": 0.2627986348122867, "acc_norm_stderr": 0.012862523175351331, "acc_stderr": 0.01222420209706329}, "multiple_choice": {"acc": 0.2735690235690236, "acc_norm": 0.2878787878787879, "acc_norm_stderr": 0.009290733161670155, "acc_stderr": 0.009147424438490745}, "pick_the_most_correct_option": {"acc": 0.22866894197952217, "acc_norm": 0.22866894197952217, "acc_norm_stderr": 0.012272853582540806, "acc_stderr": 0.012272853582540806}, "qa_options": {"acc": 0.22184300341296928, "acc_norm": 0.25853242320819114, "acc_norm_stderr": 0.012794553754288673, "acc_stderr": 0.012141659068147879}}}, "boolq": {"0": {"GPT-3 Style": {"acc": 0.48933333333333334, "acc_norm": 0.6233333333333333, "acc_norm_stderr": 0.00884811049411477, "acc_stderr": 0.009128153252511649}, "after_reading": {"acc": 0.6196666666666667, "acc_norm": 0.485, "acc_norm_stderr": 0.009126121594912155, "acc_stderr": 0.008864883436857793}, "exercise": {"acc": 0.6203333333333333, "acc_norm": 0.38166666666666665, "acc_norm_stderr": 0.008870849530787627, "acc_stderr": 0.008861873799148993}, "valid_binary": {"acc": 0.5126666666666667, "acc_norm": 0.3893333333333333, "acc_norm_stderr": 0.00890378508047089, "acc_stderr": 0.00912730086383017}, "yes_no_question": {"acc": 0.6236666666666667, "acc_norm": 0.6236666666666667, "acc_norm_stderr": 0.008846558976258922, "acc_stderr": 0.008846558976258922}}, "1": {"GPT-3 Style": {"acc": 0.5403333333333333, "acc_norm": 0.5463333333333333, "acc_norm_stderr": 0.00909094544975723, "acc_stderr": 0.009100476927108948}, "after_reading": {"acc": 0.5406666666666666, "acc_norm": 0.5403333333333333, "acc_norm_stderr": 0.009100476927108948, "acc_stderr": 0.009099982269204863}, "exercise": {"acc": 0.5406666666666666, "acc_norm": 0.541, "acc_norm_stderr": 0.009099483512819305, "acc_stderr": 0.009099982269204863}, "valid_binary": {"acc": 0.5403333333333333, "acc_norm": 0.5403333333333333, "acc_norm_stderr": 0.009100476927108948, "acc_stderr": 0.009100476927108948}, "yes_no_question": {"acc": 0.6153333333333333, "acc_norm": 0.624, "acc_norm_stderr": 0.008845002997512754, "acc_stderr": 0.00888401463187693}}, "2": {"GPT-3 Style": {"acc": 0.5376666666666666, "acc_norm": 0.5733333333333334, "acc_norm_stderr": 0.009031496556538196, "acc_stderr": 0.00910428672401049}, "after_reading": {"acc": 0.5213333333333333, "acc_norm": 0.5053333333333333, "acc_norm_stderr": 0.009129711700290994, "acc_stderr": 0.009121916798841863}, "exercise": {"acc": 0.56, "acc_norm": 0.5536666666666666, "acc_norm_stderr": 0.00907748661345029, "acc_stderr": 0.009064255084676055}, "valid_binary": {"acc": 0.556, "acc_norm": 0.542, "acc_norm_stderr": 0.009097962646004978, "acc_stderr": 0.009072785596468857}, "yes_no_question": {"acc": 0.6126666666666667, "acc_norm": 0.622, "acc_norm_stderr": 0.00885427200344005, "acc_stderr": 0.008895417372116209}}, "3": {"GPT-3 Style": {"acc": 0.561, "acc_norm": 0.5776666666666667, "acc_norm_stderr": 0.009019409415904176, "acc_stderr": 0.009062029213030572}, "after_reading": {"acc": 0.55, "acc_norm": 0.545, "acc_norm_stderr": 0.009093178503605498, "acc_stderr": 0.009084465266030921}, "exercise": {"acc": 0.5726666666666667, "acc_norm": 0.564, "acc_norm_stderr": 0.009055127374988184, "acc_stderr": 0.009033293159951222}, "valid_binary": {"acc": 0.5573333333333333, "acc_norm": 0.5473333333333333, "acc_norm_stderr": 0.009089227499483243, "acc_stderr": 0.009070008341418438}, "yes_no_question": {"acc": 0.613, "acc_norm": 0.6156666666666667, "acc_norm_stderr": 0.008882569490543052, "acc_stderr": 0.008894007408882734}}, "4": {"GPT-3 Style": {"acc": 0.5606666666666666, "acc_norm": 0.575, "acc_norm_stderr": 0.009026931658379627, "acc_stderr": 0.009062775319073724}, "after_reading": {"acc": 0.5443333333333333, "acc_norm": 0.536, "acc_norm_stderr": 0.009106534814375938, "acc_stderr": 0.00909427038138736}, "exercise": {"acc": 0.581, "acc_norm": 0.5686666666666667, "acc_norm_stderr": 0.00904372116961954, "acc_stderr": 0.009009627690997004}, "valid_binary": {"acc": 0.5676666666666667, "acc_norm": 0.5533333333333333, "acc_norm_stderr": 0.00907814166393873, "acc_stderr": 0.009046234144187919}, "yes_no_question": {"acc": 0.6226666666666667, "acc_norm": 0.624, "acc_norm_stderr": 0.00884500299751275, "acc_stderr": 0.00885120015653439}}, "5": {"GPT-3 Style": {"acc": 0.564, "acc_norm": 0.581, "acc_norm_stderr": 0.009009627690997004, "acc_stderr": 0.009055127374988182}, "after_reading": {"acc": 0.5556666666666666, "acc_norm": 0.5493333333333333, "acc_norm_stderr": 0.009085680525105019, "acc_stderr": 0.00907346956924853}, "exercise": {"acc": 0.5846666666666667, "acc_norm": 0.579, "acc_norm_stderr": 0.009015547313638383, "acc_stderr": 0.008998379972670818}, "valid_binary": {"acc": 0.5763333333333334, "acc_norm": 0.5696666666666667, "acc_norm_stderr": 0.00904117061597785, "acc_stderr": 0.0090232041691723}, "yes_no_question": {"acc": 0.6216666666666667, "acc_norm": 0.624, "acc_norm_stderr": 0.008845002997512754, "acc_stderr": 0.008855801251873017}}}, "cb": {"0": {"GPT-3 style": {"acc": 0.32142857142857145, "acc_stderr": 0.06297362289056341, "f1": 0.16666666666666666}, "MNLI crowdsource": {"acc": 0.4107142857142857, "acc_stderr": 0.06633634150359538, "f1": 0.1940928270042194}, "can we infer": {"acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.2791044776119403}, "guaranteed/possible/impossible": {"acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.3166447079490558}, "justified in saying": {"acc": 0.4107142857142857, "acc_stderr": 0.06633634150359538, "f1": 0.2144878324844369}}, "1": {"GPT-3 style": {"acc": 0.35714285714285715, "acc_stderr": 0.06460957383809221, "f1": 0.2247097844112769}, "MNLI crowdsource": {"acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2842025699168556}, "can we infer": {"acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.3227969348659004}, "guaranteed/possible/impossible": {"acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2842025699168556}, "justified in saying": {"acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.3227969348659004}}, "2": {"GPT-3 style": {"acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.24232804232804236}, "MNLI crowdsource": {"acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.29715109989181393}, "can we infer": {"acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.27519379844961245}, "guaranteed/possible/impossible": {"acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.29843652282676675}, "justified in saying": {"acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.27519379844961245}}, "3": {"GPT-3 style": {"acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2075}, "MNLI crowdsource": {"acc": 0.44642857142857145, "acc_stderr": 0.067031892279424, "f1": 0.31340255400405775}, "can we infer": {"acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.311531007751938}, "guaranteed/possible/impossible": {"acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.23085585585585586}, "justified in saying": {"acc": 0.44642857142857145, "acc_stderr": 0.067031892279424, "f1": 0.29572649572649573}}, "4": {"GPT-3 style": {"acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.18421052631578946}, "MNLI crowdsource": {"acc": 0.39285714285714285, "acc_stderr": 0.06585388898066351, "f1": 0.2647907647907648}, "can we infer": {"acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.2905242905242906}, "guaranteed/possible/impossible": {"acc": 0.5178571428571429, "acc_stderr": 0.06737697508644647, "f1": 0.2908378541289934}, "justified in saying": {"acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.2854700854700854}}, "5": {"GPT-3 style": {"acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.19047619047619047}, "MNLI crowdsource": {"acc": 0.35714285714285715, "acc_stderr": 0.0646095738380922, "f1": 0.24618343550907562}, "can we infer": {"acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.2798088410991637}, "guaranteed/possible/impossible": {"acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.2660493827160494}, "justified in saying": {"acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2524875621890547}}}, "copa": {"0": {"best_option": {"acc": 0.58, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605, "acc_stderr": 0.049604496374885836}, "cause_effect": {"acc": 0.59, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912, "acc_stderr": 0.049431107042371025}, "choose": {"acc": 0.58, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332, "acc_stderr": 0.049604496374885836}, "i_am_hesitating": {"acc": 0.56, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912, "acc_stderr": 0.049888765156985884}, "plausible_alternatives": {"acc": 0.56, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605, "acc_stderr": 0.049888765156985884}}, "1": {"best_option": {"acc": 0.53, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919, "acc_stderr": 0.05016135580465919}, "cause_effect": {"acc": 0.54, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332, "acc_stderr": 0.05009082659620332}, "choose": {"acc": 0.55, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.05}, "i_am_hesitating": {"acc": 0.48, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996, "acc_stderr": 0.050211673156867795}, "plausible_alternatives": {"acc": 0.52, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332, "acc_stderr": 0.050211673156867795}}, "2": {"best_option": {"acc": 0.55, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912, "acc_stderr": 0.05}, "cause_effect": {"acc": 0.56, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.04988876515698589}, "choose": {"acc": 0.55, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912, "acc_stderr": 0.05}, "i_am_hesitating": {"acc": 0.52, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.050211673156867795}, "plausible_alternatives": {"acc": 0.53, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.050161355804659205}}, "3": {"best_option": {"acc": 0.55, "acc_norm": 0.55, "acc_norm_stderr": 0.05, "acc_stderr": 0.05}, "cause_effect": {"acc": 0.54, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.05009082659620333}, "choose": {"acc": 0.53, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605, "acc_stderr": 0.05016135580465919}, "i_am_hesitating": {"acc": 0.49, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911, "acc_stderr": 0.05024183937956912}, "plausible_alternatives": {"acc": 0.52, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911, "acc_stderr": 0.050211673156867795}}, "4": {"best_option": {"acc": 0.51, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911, "acc_stderr": 0.05024183937956911}, "cause_effect": {"acc": 0.55, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333, "acc_stderr": 0.05}, "choose": {"acc": 0.54, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912, "acc_stderr": 0.05009082659620333}, "i_am_hesitating": {"acc": 0.47, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605, "acc_stderr": 0.05016135580465919}, "plausible_alternatives": {"acc": 0.51, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.05024183937956911}}, "5": {"best_option": {"acc": 0.55, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101, "acc_stderr": 0.05}, "cause_effect": {"acc": 0.54, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.05009082659620333}, "choose": {"acc": 0.53, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.050161355804659205}, "i_am_hesitating": {"acc": 0.5, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911, "acc_stderr": 0.050251890762960605}, "plausible_alternatives": {"acc": 0.51, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795, "acc_stderr": 0.05024183937956911}}}, "e2e_nlg_cleaned": {"0": {"coherent_text": {"bleu": 1.4085336184354111, "bleu_stderr": 0.05741951405804131, "rouge1_fmeasure": 0.16506378620343637, "rouge1_fmeasure_stderr": 0.0022294407692459474, "rouge1_precision": 0.13228526132614984, "rouge1_precision_stderr": 0.0020013074393031836, "rouge1_recall": 0.2369325887389989, "rouge1_recall_stderr": 0.0027790980608073646, "rouge2_fmeasure": 0.0413168613300981, "rouge2_fmeasure_stderr": 0.0011779113504419888, "rouge2_precision": 0.034003030527238576, "rouge2_precision_stderr": 0.0010025662026581091, "rouge2_recall": 0.056957962707056595, "rouge2_recall_stderr": 0.0016005937753295783, "rougeL_fmeasure": 0.14268631130584333, "rougeL_fmeasure_stderr": 0.0014826828522232203, "rougeL_precision": 0.11307449761220935, "rougeL_precision_stderr": 0.0012999325612706172, "rougeL_recall": 0.208842612528325, "rougeL_recall_stderr": 0.0020062255755377858, "rougeLsum_fmeasure": 0.13688623513784934, "rougeLsum_fmeasure_stderr": 0.0017661120751764666, "rougeLsum_precision": 0.10960115777847065, "rougeLsum_precision_stderr": 0.001579915881101131, "rougeLsum_recall": 0.19748155077377938, "rougeLsum_recall_stderr": 0.0022590044053826777}, "create_text_for_me": {"bleu": 2.703242330052237, "bleu_stderr": 0.053740475370982206, "rouge1_fmeasure": 0.3195200501284644, "rouge1_fmeasure_stderr": 0.0029128906590861338, "rouge1_precision": 0.2661363538943579, "rouge1_precision_stderr": 0.002367715966031621, "rouge1_recall": 0.43300283554036917, "rouge1_recall_stderr": 0.004390407342450644, "rouge2_fmeasure": 0.13691922129643072, "rouge2_fmeasure_stderr": 0.0012702596895246712, "rouge2_precision": 0.11474242753676482, "rouge2_precision_stderr": 0.0010312600650423582, "rouge2_recall": 0.1866895759452563, "rouge2_recall_stderr": 0.002052535203353899, "rougeL_fmeasure": 0.21271540347370638, "rougeL_fmeasure_stderr": 0.0016500637313875428, "rougeL_precision": 0.17937558305738294, "rougeL_precision_stderr": 0.0013720245995724903, "rougeL_recall": 0.28616889513557914, "rougeL_recall_stderr": 0.0026317983935095325, "rougeLsum_fmeasure": 0.26161394912968283, "rougeLsum_fmeasure_stderr": 0.0022526565471884855, "rougeLsum_precision": 0.21948638044662674, "rougeLsum_precision_stderr": 0.0018609668228193143, "rougeLsum_recall": 0.3521509345321294, "rougeLsum_recall_stderr": 0.00340514324563439}, "generate_gramatically_correct_text": {"bleu": 3.33689116446375, "bleu_stderr": 0.061087011177673324, "rouge1_fmeasure": 0.1544874561171709, "rouge1_fmeasure_stderr": 0.0010331568296333966, "rouge1_precision": 0.16350018472386488, "rouge1_precision_stderr": 0.0009748274524219786, "rouge1_recall": 0.15345481937904124, "rouge1_recall_stderr": 0.0013096963261815264, "rouge2_fmeasure": 0.10374767270154109, "rouge2_fmeasure_stderr": 0.0009552767021848785, "rouge2_precision": 0.10930581072628082, "rouge2_precision_stderr": 0.0009544493807060682, "rouge2_recall": 0.10394007426189322, "rouge2_recall_stderr": 0.0011356818972608751, "rougeL_fmeasure": 0.1544874561171709, "rougeL_fmeasure_stderr": 0.0010331568296333966, "rougeL_precision": 0.16350018472386488, "rougeL_precision_stderr": 0.0009748274524219786, "rougeL_recall": 0.15345481937904124, "rougeL_recall_stderr": 0.0013096963261815264, "rougeLsum_fmeasure": 0.15232644862442798, "rougeLsum_fmeasure_stderr": 0.000994235301055403, "rougeLsum_precision": 0.16126223153775923, "rougeLsum_precision_stderr": 0.0009358067078434506, "rougeLsum_recall": 0.15130017670533033, "rougeLsum_recall_stderr": 0.0012746322385110529}, "generate_text_restaurant": {"bleu": 0.11176674048639335, "bleu_stderr": 0.025745526624568513, "rouge1_fmeasure": 0.15222302512937821, "rouge1_fmeasure_stderr": 0.0013013498465447167, "rouge1_precision": 0.16696437758477956, "rouge1_precision_stderr": 0.0017859239587553095, "rouge1_recall": 0.15714888553652667, "rouge1_recall_stderr": 0.0014080404762761625, "rouge2_fmeasure": 0.010123335458248412, "rouge2_fmeasure_stderr": 0.00043360666103113316, "rouge2_precision": 0.009953161364593704, "rouge2_precision_stderr": 0.00045153060703839287, "rouge2_recall": 0.011372231163400725, "rouge2_recall_stderr": 0.00047796121503254033, "rougeL_fmeasure": 0.11199161031913281, "rougeL_fmeasure_stderr": 0.0009318642813866649, "rougeL_precision": 0.12080392040996726, "rougeL_precision_stderr": 0.001200893081884765, "rougeL_recall": 0.11779742301789177, "rougeL_recall_stderr": 0.0011408283583082188, "rougeLsum_fmeasure": 0.13868103668142837, "rougeLsum_fmeasure_stderr": 0.0011150022939164787, "rougeLsum_precision": 0.15176134198199345, "rougeLsum_precision_stderr": 0.0015534141731862994, "rougeLsum_recall": 0.14365210992596641, "rougeLsum_recall_stderr": 0.0012440730468959943}, "text": {"bleu": 2.312044583390139, "bleu_stderr": 0.0395109885826077, "rouge1_fmeasure": 0.18396830789775534, "rouge1_fmeasure_stderr": 0.0019217889423799447, "rouge1_precision": 0.1483234108399301, "rouge1_precision_stderr": 0.0018820269691433504, "rouge1_recall": 0.2665312132559497, "rouge1_recall_stderr": 0.0022782588706576823, "rouge2_fmeasure": 0.07857762779721571, "rouge2_fmeasure_stderr": 0.0010324442678352934, "rouge2_precision": 0.06330225911047903, "rouge2_precision_stderr": 0.000929977214652403, "rouge2_recall": 0.1144099347030503, "rouge2_recall_stderr": 0.0013911841551972658, "rougeL_fmeasure": 0.16491978865694182, "rougeL_fmeasure_stderr": 0.0015173618055678087, "rougeL_precision": 0.13168588320305488, "rougeL_precision_stderr": 0.0014088056357095735, "rougeL_recall": 0.24187944010259957, "rougeL_recall_stderr": 0.001991719734240969, "rougeLsum_fmeasure": 0.16382995952828802, "rougeLsum_fmeasure_stderr": 0.0016389684965023624, "rougeLsum_precision": 0.13170067737530292, "rougeLsum_precision_stderr": 0.001562161536791986, "rougeLsum_recall": 0.2380165156086324, "rougeLsum_recall_stderr": 0.0020441457742624673}}, "1": {"coherent_text": {"bleu": 4.729286166275417, "bleu_stderr": 0.09128304389641625, "rouge1_fmeasure": 0.2892038317215652, "rouge1_fmeasure_stderr": 0.0025869454710142777, "rouge1_precision": 0.3408358446419251, "rouge1_precision_stderr": 0.0034116541291492057, "rouge1_recall": 0.2783365471883401, "rouge1_recall_stderr": 0.002737152709268981, "rouge2_fmeasure": 0.09705173957954942, "rouge2_fmeasure_stderr": 0.0015453194099685405, "rouge2_precision": 0.11786217798858512, "rouge2_precision_stderr": 0.0020524631363241412, "rouge2_recall": 0.09241456760956686, "rouge2_recall_stderr": 0.0015313690129086298, "rougeL_fmeasure": 0.21222627239556746, "rougeL_fmeasure_stderr": 0.0019998631000071967, "rougeL_precision": 0.25216134633862136, "rougeL_precision_stderr": 0.0027436356295732754, "rougeL_recall": 0.20399063384073168, "rougeL_recall_stderr": 0.002098237813401181, "rougeLsum_fmeasure": 0.23867678360949154, "rougeLsum_fmeasure_stderr": 0.0022704869608702, "rougeLsum_precision": 0.28273246045224193, "rougeLsum_precision_stderr": 0.0030427081908894252, "rougeLsum_recall": 0.22924073727175148, "rougeLsum_recall_stderr": 0.0023626083063246254}, "create_text_for_me": {"bleu": 4.577776049140263, "bleu_stderr": 0.09034061701953547, "rouge1_fmeasure": 0.29090627143470194, "rouge1_fmeasure_stderr": 0.0024330971957175203, "rouge1_precision": 0.34100807827295837, "rouge1_precision_stderr": 0.003184063014013613, "rouge1_recall": 0.27941656720882674, "rouge1_recall_stderr": 0.0026026095744065953, "rouge2_fmeasure": 0.09291021571347792, "rouge2_fmeasure_stderr": 0.0015027135995425269, "rouge2_precision": 0.11175648476464418, "rouge2_precision_stderr": 0.0019681372052978165, "rouge2_recall": 0.08832198666750592, "rouge2_recall_stderr": 0.0014790311360637835, "rougeL_fmeasure": 0.21213952158968352, "rougeL_fmeasure_stderr": 0.0018872143094313097, "rougeL_precision": 0.25053169214166077, "rougeL_precision_stderr": 0.0025671894408817466, "rougeL_recall": 0.20342961186323133, "rougeL_recall_stderr": 0.001994180509072628, "rougeLsum_fmeasure": 0.2393285330033846, "rougeLsum_fmeasure_stderr": 0.00214964727816577, "rougeLsum_precision": 0.28172377076654426, "rougeLsum_precision_stderr": 0.002852857226376121, "rougeLsum_recall": 0.22946240670401793, "rougeLsum_recall_stderr": 0.002255076858855054}, "generate_gramatically_correct_text": {"bleu": 4.231103023669522, "bleu_stderr": 0.06401228873780763, "rouge1_fmeasure": 0.21822213931750256, "rouge1_fmeasure_stderr": 0.002101989165296421, "rouge1_precision": 0.22876696491722354, "rouge1_precision_stderr": 0.002309289082178887, "rouge1_recall": 0.22418518523376774, "rouge1_recall_stderr": 0.0024608018120844447, "rouge2_fmeasure": 0.11246784846792322, "rouge2_fmeasure_stderr": 0.0011969645761367486, "rouge2_precision": 0.11900463798533546, "rouge2_precision_stderr": 0.0013220328662893331, "rouge2_recall": 0.11426547711399747, "rouge2_recall_stderr": 0.0013755970980597794, "rougeL_fmeasure": 0.18786846421672448, "rougeL_fmeasure_stderr": 0.001330092385386827, "rougeL_precision": 0.19721866991989792, "rougeL_precision_stderr": 0.001448486033755209, "rougeL_recall": 0.19219429418598927, "rougeL_recall_stderr": 0.001702222043237259, "rougeLsum_fmeasure": 0.19423470819963112, "rougeLsum_fmeasure_stderr": 0.001652146284622351, "rougeLsum_precision": 0.2036594715170169, "rougeLsum_precision_stderr": 0.0017870596309090383, "rougeLsum_recall": 0.19919852385897865, "rougeLsum_recall_stderr": 0.002011582797896158}, "generate_text_restaurant": {"bleu": 5.3012905706855715, "bleu_stderr": 0.06983249125236993, "rouge1_fmeasure": 0.32162747895375954, "rouge1_fmeasure_stderr": 0.0020771074301500782, "rouge1_precision": 0.3815413917530348, "rouge1_precision_stderr": 0.002837174970345969, "rouge1_recall": 0.3064552216042878, "rouge1_recall_stderr": 0.0023886076473393645, "rouge2_fmeasure": 0.10817189459012165, "rouge2_fmeasure_stderr": 0.0015550558960603117, "rouge2_precision": 0.13086483275629, "rouge2_precision_stderr": 0.0020280885765991885, "rouge2_recall": 0.1025349516561498, "rouge2_recall_stderr": 0.001571669556321608, "rougeL_fmeasure": 0.23379701509505144, "rougeL_fmeasure_stderr": 0.0016853591821340379, "rougeL_precision": 0.27916128217581454, "rougeL_precision_stderr": 0.0023638984947284046, "rougeL_recall": 0.2222943424941319, "rougeL_recall_stderr": 0.0018853089294649107, "rougeLsum_fmeasure": 0.26334461160376826, "rougeLsum_fmeasure_stderr": 0.0019172374126938273, "rougeLsum_precision": 0.3136019413612245, "rougeLsum_precision_stderr": 0.002623636065057541, "rougeLsum_recall": 0.2503472789320967, "rougeLsum_recall_stderr": 0.002117352162606577}, "text": {"bleu": 5.658373765079044, "bleu_stderr": 0.08499855577351746, "rouge1_fmeasure": 0.31664965729123945, "rouge1_fmeasure_stderr": 0.0020607356438432697, "rouge1_precision": 0.3785635846368343, "rouge1_precision_stderr": 0.0030612871591419147, "rouge1_recall": 0.30450164969564714, "rouge1_recall_stderr": 0.0022564011527415394, "rouge2_fmeasure": 0.11238103667987336, "rouge2_fmeasure_stderr": 0.0015100568087131015, "rouge2_precision": 0.13934496500807864, "rouge2_precision_stderr": 0.00216195315567069, "rouge2_recall": 0.10702848594772853, "rouge2_recall_stderr": 0.0014968393936312507, "rougeL_fmeasure": 0.2374686347495831, "rougeL_fmeasure_stderr": 0.0016753126850071298, "rougeL_precision": 0.28631430972883853, "rougeL_precision_stderr": 0.002617927639070605, "rougeL_recall": 0.2283811920065958, "rougeL_recall_stderr": 0.0018138508581349217, "rougeLsum_fmeasure": 0.2632560786781301, "rougeLsum_fmeasure_stderr": 0.0018894463768983068, "rougeLsum_precision": 0.31633107781620623, "rougeLsum_precision_stderr": 0.0028315570567799433, "rougeLsum_recall": 0.25293146488273016, "rougeLsum_recall_stderr": 0.0020207172248228092}}, "2": {"coherent_text": {"bleu": 6.325316845200212, "bleu_stderr": 0.09823383956529014, "rouge1_fmeasure": 0.33385083240638835, "rouge1_fmeasure_stderr": 0.0022057300734858753, "rouge1_precision": 0.3908301753738232, "rouge1_precision_stderr": 0.0031422044941371253, "rouge1_recall": 0.32494169596300476, "rouge1_recall_stderr": 0.0024924666531749825, "rouge2_fmeasure": 0.12480576931000954, "rouge2_fmeasure_stderr": 0.001582754162108835, "rouge2_precision": 0.1514609363136513, "rouge2_precision_stderr": 0.0022477501689905873, "rouge2_recall": 0.12052118677866239, "rouge2_recall_stderr": 0.0016199084429215386, "rougeL_fmeasure": 0.2482760515483937, "rougeL_fmeasure_stderr": 0.0017935997104643916, "rougeL_precision": 0.293562283125087, "rougeL_precision_stderr": 0.002707140102409516, "rougeL_recall": 0.24127140452116988, "rougeL_recall_stderr": 0.0019870656915090814, "rougeLsum_fmeasure": 0.27814692011572395, "rougeLsum_fmeasure_stderr": 0.00202476127925843, "rougeLsum_precision": 0.32736403463849806, "rougeLsum_precision_stderr": 0.002914041154580964, "rougeLsum_recall": 0.2701473844458722, "rougeLsum_recall_stderr": 0.0022228285101149096}, "create_text_for_me": {"bleu": 5.98205212345435, "bleu_stderr": 0.1280571718069931, "rouge1_fmeasure": 0.32884340089308617, "rouge1_fmeasure_stderr": 0.002135142045723192, "rouge1_precision": 0.3823214924637971, "rouge1_precision_stderr": 0.003024709228079845, "rouge1_recall": 0.3204650885914036, "rouge1_recall_stderr": 0.002430593485338909, "rouge2_fmeasure": 0.11731827518171299, "rouge2_fmeasure_stderr": 0.0015444189662990626, "rouge2_precision": 0.14073383940982426, "rouge2_precision_stderr": 0.002136791451462909, "rouge2_recall": 0.11362566019027333, "rouge2_recall_stderr": 0.001592486151354374, "rougeL_fmeasure": 0.24308318109830301, "rougeL_fmeasure_stderr": 0.001718910616546924, "rougeL_precision": 0.2851163980403521, "rougeL_precision_stderr": 0.002571830567593308, "rougeL_recall": 0.2366396569421376, "rougeL_recall_stderr": 0.0019279427376296453, "rougeLsum_fmeasure": 0.2736078163019124, "rougeLsum_fmeasure_stderr": 0.001965703958545944, "rougeLsum_precision": 0.31962238317070146, "rougeLsum_precision_stderr": 0.002803107271378859, "rougeLsum_recall": 0.26621396952055804, "rougeLsum_recall_stderr": 0.002177094542934803}, "generate_gramatically_correct_text": {"bleu": 5.525451650396909, "bleu_stderr": 0.1444467494539742, "rouge1_fmeasure": 0.26534001970520577, "rouge1_fmeasure_stderr": 0.0025743732024496244, "rouge1_precision": 0.2834490220270683, "rouge1_precision_stderr": 0.0030414084396847606, "rouge1_recall": 0.2715933334719839, "rouge1_recall_stderr": 0.002848612162614692, "rouge2_fmeasure": 0.12416901504237551, "rouge2_fmeasure_stderr": 0.0014418832805010986, "rouge2_precision": 0.13405990343107269, "rouge2_precision_stderr": 0.0017363915410273162, "rouge2_recall": 0.12632320690490031, "rouge2_recall_stderr": 0.001580690379939971, "rougeL_fmeasure": 0.21281653093345984, "rougeL_fmeasure_stderr": 0.0016678452099069705, "rougeL_precision": 0.22739524397837393, "rougeL_precision_stderr": 0.002045754856820925, "rougeL_recall": 0.21790717317346972, "rougeL_recall_stderr": 0.001977682176352203, "rougeLsum_fmeasure": 0.2284401060917875, "rougeLsum_fmeasure_stderr": 0.0021061890580456274, "rougeLsum_precision": 0.24440894566677487, "rougeLsum_precision_stderr": 0.0025218643599198604, "rougeLsum_recall": 0.23358308890323742, "rougeLsum_recall_stderr": 0.0023681355345237325}, "generate_text_restaurant": {"bleu": 6.484621213756497, "bleu_stderr": 0.0974863563868723, "rouge1_fmeasure": 0.3420522066441051, "rouge1_fmeasure_stderr": 0.0020985317696014232, "rouge1_precision": 0.41139978305209435, "rouge1_precision_stderr": 0.003067700206274608, "rouge1_recall": 0.3252856106278531, "rouge1_recall_stderr": 0.0024570831951622046, "rouge2_fmeasure": 0.12966947477583363, "rouge2_fmeasure_stderr": 0.0016114647269419636, "rouge2_precision": 0.16044952433810813, "rouge2_precision_stderr": 0.0022415019504744573, "rouge2_recall": 0.12295995789487724, "rouge2_recall_stderr": 0.0016908155548698506, "rougeL_fmeasure": 0.25601590775495564, "rougeL_fmeasure_stderr": 0.0017579676075034684, "rougeL_precision": 0.3101968039122714, "rougeL_precision_stderr": 0.0026559494676439695, "rougeL_recall": 0.2432211605884282, "rougeL_recall_stderr": 0.0020134767570951996, "rougeLsum_fmeasure": 0.2842749213664702, "rougeLsum_fmeasure_stderr": 0.001992190307244928, "rougeLsum_precision": 0.34330225686796983, "rougeLsum_precision_stderr": 0.002884969316299285, "rougeLsum_recall": 0.26983375724985587, "rougeLsum_recall_stderr": 0.002240579967780497}, "text": {"bleu": 6.917215486681154, "bleu_stderr": 0.09030336208671559, "rouge1_fmeasure": 0.3365847325089085, "rouge1_fmeasure_stderr": 0.0021240478562747096, "rouge1_precision": 0.40102908401240517, "rouge1_precision_stderr": 0.0031305165635581666, "rouge1_recall": 0.3245770394369534, "rouge1_recall_stderr": 0.002380280848054982, "rouge2_fmeasure": 0.13240317910861094, "rouge2_fmeasure_stderr": 0.001585927980196938, "rouge2_precision": 0.1624015628216895, "rouge2_precision_stderr": 0.0022128114021614867, "rouge2_recall": 0.12717184459111075, "rouge2_recall_stderr": 0.0016440230921468948, "rougeL_fmeasure": 0.25697032555307603, "rougeL_fmeasure_stderr": 0.0017681623995959028, "rougeL_precision": 0.3078746669304236, "rougeL_precision_stderr": 0.0026746765410402343, "rougeL_recall": 0.24821866410165572, "rougeL_recall_stderr": 0.001975259655202282, "rougeLsum_fmeasure": 0.28336588654052414, "rougeLsum_fmeasure_stderr": 0.0019832801111781904, "rougeLsum_precision": 0.3384966177161513, "rougeLsum_precision_stderr": 0.002883629760587024, "rougeLsum_recall": 0.27305479728579, "rougeLsum_recall_stderr": 0.0021713449800655122}}, "3": {"coherent_text": {"bleu": 7.093242387648388, "bleu_stderr": 0.1779108642695036, "rouge1_fmeasure": 0.3468468278255215, "rouge1_fmeasure_stderr": 0.002126607440022899, "rouge1_precision": 0.4033568597868611, "rouge1_precision_stderr": 0.0030439856617461825, "rouge1_recall": 0.3393497221509125, "rouge1_recall_stderr": 0.0024495138617378286, "rouge2_fmeasure": 0.13345925813528606, "rouge2_fmeasure_stderr": 0.0016050391064121614, "rouge2_precision": 0.1603885963824591, "rouge2_precision_stderr": 0.002211321437110491, "rouge2_recall": 0.1297128662599877, "rouge2_recall_stderr": 0.0016715601470477192, "rougeL_fmeasure": 0.25781869559651055, "rougeL_fmeasure_stderr": 0.0017250105332014863, "rougeL_precision": 0.30327882804864414, "rougeL_precision_stderr": 0.0026682405889953253, "rougeL_recall": 0.2518780545862424, "rougeL_recall_stderr": 0.0019409034909989161, "rougeLsum_fmeasure": 0.28922616836791826, "rougeLsum_fmeasure_stderr": 0.0019740744474346238, "rougeLsum_precision": 0.33832600518727873, "rougeLsum_precision_stderr": 0.002866030451437672, "rougeLsum_recall": 0.2824307369414572, "rougeLsum_recall_stderr": 0.0021987427091062425}, "create_text_for_me": {"bleu": 6.863369305798137, "bleu_stderr": 0.15945748355314382, "rouge1_fmeasure": 0.342206180898298, "rouge1_fmeasure_stderr": 0.0021010446350658595, "rouge1_precision": 0.39244673058197366, "rouge1_precision_stderr": 0.00291042027182271, "rouge1_recall": 0.3356108550535503, "rouge1_recall_stderr": 0.002419884948866489, "rouge2_fmeasure": 0.12734114879849334, "rouge2_fmeasure_stderr": 0.001589185479506862, "rouge2_precision": 0.149747180591347, "rouge2_precision_stderr": 0.002068565282156403, "rouge2_recall": 0.12431399945617358, "rouge2_recall_stderr": 0.0016576108529010333, "rougeL_fmeasure": 0.25304733592238204, "rougeL_fmeasure_stderr": 0.0017029355919681117, "rougeL_precision": 0.2929476916339765, "rougeL_precision_stderr": 0.00249955074163189, "rougeL_recall": 0.24778818042905212, "rougeL_recall_stderr": 0.0019126314450433883, "rougeLsum_fmeasure": 0.2851145615546105, "rougeLsum_fmeasure_stderr": 0.0019583190063539803, "rougeLsum_precision": 0.32865423091372126, "rougeLsum_precision_stderr": 0.0027286585155264402, "rougeLsum_recall": 0.2790170412547052, "rougeLsum_recall_stderr": 0.0021770844165001626}, "generate_gramatically_correct_text": {"bleu": 6.8137963757639595, "bleu_stderr": 0.20255562203924876, "rouge1_fmeasure": 0.29832265261949864, "rouge1_fmeasure_stderr": 0.002682363598114479, "rouge1_precision": 0.3270546311530774, "rouge1_precision_stderr": 0.0033260484118045196, "rouge1_recall": 0.30290304692810277, "rouge1_recall_stderr": 0.0029793997242539795, "rouge2_fmeasure": 0.1327243773594466, "rouge2_fmeasure_stderr": 0.0016010342153913112, "rouge2_precision": 0.146059799869631, "rouge2_precision_stderr": 0.0019394392606377293, "rouge2_recall": 0.13509651368601627, "rouge2_recall_stderr": 0.0017660311848326784, "rougeL_fmeasure": 0.23091319790847228, "rougeL_fmeasure_stderr": 0.001809456729054163, "rougeL_precision": 0.25289429854529516, "rougeL_precision_stderr": 0.0023232203307966158, "rougeL_recall": 0.23497554580132518, "rougeL_recall_stderr": 0.002126463940220678, "rougeLsum_fmeasure": 0.2526729166449464, "rougeLsum_fmeasure_stderr": 0.0022317763780196186, "rougeLsum_precision": 0.2773139281135476, "rougeLsum_precision_stderr": 0.002808432208536525, "rougeLsum_recall": 0.2565055228473518, "rougeLsum_recall_stderr": 0.0025015169643640652}, "generate_text_restaurant": {"bleu": 6.879629327338769, "bleu_stderr": 0.1346069600960464, "rouge1_fmeasure": 0.3463166802954874, "rouge1_fmeasure_stderr": 0.00213652320528259, "rouge1_precision": 0.42201728977513014, "rouge1_precision_stderr": 0.003107151077288339, "rouge1_recall": 0.3272628452554048, "rouge1_recall_stderr": 0.002461890669832865, "rouge2_fmeasure": 0.13691320451323, "rouge2_fmeasure_stderr": 0.0016811203463266734, "rouge2_precision": 0.17146778036168178, "rouge2_precision_stderr": 0.0023302870066652893, "rouge2_recall": 0.12891634697023943, "rouge2_recall_stderr": 0.0017367276208110785, "rougeL_fmeasure": 0.2610757008973968, "rougeL_fmeasure_stderr": 0.0017801310756353193, "rougeL_precision": 0.3213628033975934, "rougeL_precision_stderr": 0.0027392401350909996, "rougeL_recall": 0.24620580859495172, "rougeL_recall_stderr": 0.001997741786107464, "rougeLsum_fmeasure": 0.2896766488362631, "rougeLsum_fmeasure_stderr": 0.001994600250845987, "rougeLsum_precision": 0.3548763955773087, "rougeLsum_precision_stderr": 0.0029163728160237273, "rougeLsum_recall": 0.2732798481620792, "rougeLsum_recall_stderr": 0.0022332299942385615}, "text": {"bleu": 7.302933244369964, "bleu_stderr": 0.1527151661282377, "rouge1_fmeasure": 0.34292801400129946, "rouge1_fmeasure_stderr": 0.0020983362895782443, "rouge1_precision": 0.40976641043825285, "rouge1_precision_stderr": 0.003078900083587585, "rouge1_recall": 0.3298207802659436, "rouge1_recall_stderr": 0.002370269980991039, "rouge2_fmeasure": 0.1375143860984762, "rouge2_fmeasure_stderr": 0.001597502116017482, "rouge2_precision": 0.16923415682313503, "rouge2_precision_stderr": 0.0022309657925827548, "rouge2_recall": 0.13169306775839348, "rouge2_recall_stderr": 0.0016574071058421535, "rougeL_fmeasure": 0.26487498731759745, "rougeL_fmeasure_stderr": 0.0017575023861850282, "rougeL_precision": 0.31910429949813013, "rougeL_precision_stderr": 0.00271697238304695, "rougeL_recall": 0.25477988953379643, "rougeL_recall_stderr": 0.001954868697916928, "rougeLsum_fmeasure": 0.2914768408781806, "rougeLsum_fmeasure_stderr": 0.0019710026406425415, "rougeLsum_precision": 0.35002435680776456, "rougeLsum_precision_stderr": 0.002909025689835447, "rougeLsum_recall": 0.27988532121673076, "rougeLsum_recall_stderr": 0.002164775670324916}}, "4": {"coherent_text": {"bleu": 7.441380932329685, "bleu_stderr": 0.13415864466690663, "rouge1_fmeasure": 0.3513421927671594, "rouge1_fmeasure_stderr": 0.0021279258327609294, "rouge1_precision": 0.40930270509361055, "rouge1_precision_stderr": 0.003082794337886431, "rouge1_recall": 0.34406073111724306, "rouge1_recall_stderr": 0.0024467984658659457, "rouge2_fmeasure": 0.139368667490815, "rouge2_fmeasure_stderr": 0.0016374065418968793, "rouge2_precision": 0.16770678005567702, "rouge2_precision_stderr": 0.0022910300764590334, "rouge2_recall": 0.1356936401482478, "rouge2_recall_stderr": 0.0017118286189666942, "rougeL_fmeasure": 0.2632971395760134, "rougeL_fmeasure_stderr": 0.001761093443585716, "rougeL_precision": 0.30955103142076024, "rougeL_precision_stderr": 0.0026954850190455738, "rougeL_recall": 0.25780563970283943, "rougeL_recall_stderr": 0.0019854199620409053, "rougeLsum_fmeasure": 0.294208873461138, "rougeLsum_fmeasure_stderr": 0.001978637458277599, "rougeLsum_precision": 0.34462560843141665, "rougeLsum_precision_stderr": 0.0028969602572112584, "rougeLsum_recall": 0.2875465717034684, "rougeLsum_recall_stderr": 0.002202341197956502}, "create_text_for_me": {"bleu": 7.213329948258112, "bleu_stderr": 0.1504445078411636, "rouge1_fmeasure": 0.34597281761424564, "rouge1_fmeasure_stderr": 0.0021117138542066263, "rouge1_precision": 0.39870625613730687, "rouge1_precision_stderr": 0.0030059139760784137, "rouge1_recall": 0.3401793704440513, "rouge1_recall_stderr": 0.00244816453017379, "rouge2_fmeasure": 0.1322742849122928, "rouge2_fmeasure_stderr": 0.0016280655196310467, "rouge2_precision": 0.15639401362724684, "rouge2_precision_stderr": 0.002182860663855212, "rouge2_recall": 0.12970046691236706, "rouge2_recall_stderr": 0.001719867215235167, "rougeL_fmeasure": 0.25839347897511217, "rougeL_fmeasure_stderr": 0.001739652960879094, "rougeL_precision": 0.30042871354521805, "rougeL_precision_stderr": 0.002604676027141301, "rougeL_recall": 0.2538632272987309, "rougeL_recall_stderr": 0.0019749848838672476, "rougeLsum_fmeasure": 0.2899260055449036, "rougeLsum_fmeasure_stderr": 0.0019853018337260124, "rougeLsum_precision": 0.33569946464927397, "rougeLsum_precision_stderr": 0.002827255616797676, "rougeLsum_recall": 0.2846056877350737, "rougeLsum_recall_stderr": 0.002227786950064511}, "generate_gramatically_correct_text": {"bleu": 7.341198614648136, "bleu_stderr": 0.17045073548615564, "rouge1_fmeasure": 0.31596377144440585, "rouge1_fmeasure_stderr": 0.0026655508139599173, "rouge1_precision": 0.35350382405858616, "rouge1_precision_stderr": 0.003442922432389858, "rouge1_recall": 0.3188764804549842, "rouge1_recall_stderr": 0.0029638694103824277, "rouge2_fmeasure": 0.13722355902976058, "rouge2_fmeasure_stderr": 0.0016747877599416919, "rouge2_precision": 0.1549567262980173, "rouge2_precision_stderr": 0.002127947989131943, "rouge2_recall": 0.13893389284637747, "rouge2_recall_stderr": 0.0018236049827216453, "rougeL_fmeasure": 0.2408545283139996, "rougeL_fmeasure_stderr": 0.0018742380511928072, "rougeL_precision": 0.26952618807409345, "rougeL_precision_stderr": 0.002533331450712522, "rougeL_recall": 0.24417509331372464, "rougeL_recall_stderr": 0.002199216476423094, "rougeLsum_fmeasure": 0.26664577905196357, "rougeLsum_fmeasure_stderr": 0.0022767260952207273, "rougeLsum_precision": 0.2985654514117335, "rougeLsum_precision_stderr": 0.0029755296285733485, "rougeLsum_recall": 0.2693279956215855, "rougeLsum_recall_stderr": 0.0025433959718711577}, "generate_text_restaurant": {"bleu": 7.043340928793498, "bleu_stderr": 0.17457577578396632, "rouge1_fmeasure": 0.3484130556989747, "rouge1_fmeasure_stderr": 0.0021567720832225755, "rouge1_precision": 0.42849398140403416, "rouge1_precision_stderr": 0.003154039113080988, "rouge1_recall": 0.3260253265844876, "rouge1_recall_stderr": 0.0024300314619900886, "rouge2_fmeasure": 0.13896898011991943, "rouge2_fmeasure_stderr": 0.001696565627297103, "rouge2_precision": 0.1755199620636604, "rouge2_precision_stderr": 0.002326078614960514, "rouge2_recall": 0.12942494945873848, "rouge2_recall_stderr": 0.0017198177455500956, "rougeL_fmeasure": 0.26571281983219025, "rougeL_fmeasure_stderr": 0.0018278399179337257, "rougeL_precision": 0.3295172578321846, "rougeL_precision_stderr": 0.0027851684130843772, "rougeL_recall": 0.24845018656704826, "rougeL_recall_stderr": 0.002015612153914146, "rougeLsum_fmeasure": 0.2923263218516018, "rougeLsum_fmeasure_stderr": 0.0020524443622954285, "rougeLsum_precision": 0.3613892288819798, "rougeLsum_precision_stderr": 0.003004023862876739, "rougeLsum_recall": 0.2729143969722366, "rougeLsum_recall_stderr": 0.0022213221391673625}, "text": {"bleu": 7.669963629530005, "bleu_stderr": 0.19346868748686652, "rouge1_fmeasure": 0.34959289046921094, "rouge1_fmeasure_stderr": 0.0020793186867037474, "rouge1_precision": 0.41822864707123897, "rouge1_precision_stderr": 0.0031091354286543996, "rouge1_recall": 0.3361316604502726, "rouge1_recall_stderr": 0.0023559546948861898, "rouge2_fmeasure": 0.14197862193928545, "rouge2_fmeasure_stderr": 0.001637642338037844, "rouge2_precision": 0.1737722798289324, "rouge2_precision_stderr": 0.0022559830525788267, "rouge2_recall": 0.13630282002247948, "rouge2_recall_stderr": 0.001690717470047277, "rougeL_fmeasure": 0.270791556407417, "rougeL_fmeasure_stderr": 0.0017960817490802496, "rougeL_precision": 0.32559296595574067, "rougeL_precision_stderr": 0.00272622024383481, "rougeL_recall": 0.260656215712442, "rougeL_recall_stderr": 0.0019981009630238747, "rougeLsum_fmeasure": 0.29703338834518844, "rougeLsum_fmeasure_stderr": 0.002014348371578559, "rougeLsum_precision": 0.3561490228639673, "rougeLsum_precision_stderr": 0.002943695124328949, "rougeLsum_recall": 0.28548991550740394, "rougeLsum_recall_stderr": 0.0022090994833757244}}, "5": {"coherent_text": {"bleu": 7.5737114766827744, "bleu_stderr": 0.16631977129206255, "rouge1_fmeasure": 0.3550742864577696, "rouge1_fmeasure_stderr": 0.0021015187822019713, "rouge1_precision": 0.41687585365688856, "rouge1_precision_stderr": 0.0031195723945421903, "rouge1_recall": 0.3459752611920822, "rouge1_recall_stderr": 0.002424143041978818, "rouge2_fmeasure": 0.1433273164318412, "rouge2_fmeasure_stderr": 0.0016448122877788167, "rouge2_precision": 0.1733553595449332, "rouge2_precision_stderr": 0.0023061322348589372, "rouge2_recall": 0.13907964535601638, "rouge2_recall_stderr": 0.001719596537412042, "rougeL_fmeasure": 0.2689262922478298, "rougeL_fmeasure_stderr": 0.0017684452634382998, "rougeL_precision": 0.3185451706746064, "rougeL_precision_stderr": 0.002764987760129163, "rougeL_recall": 0.2618919651726129, "rougeL_recall_stderr": 0.001983008971819947, "rougeLsum_fmeasure": 0.29967975079613524, "rougeLsum_fmeasure_stderr": 0.001985017926935537, "rougeLsum_precision": 0.353237732771995, "rougeLsum_precision_stderr": 0.0029473597771023205, "rougeLsum_recall": 0.2916978400324908, "rougeLsum_recall_stderr": 0.0022123740894828313}, "create_text_for_me": {"bleu": 7.496072350547459, "bleu_stderr": 0.13118615529748254, "rouge1_fmeasure": 0.3526218995116698, "rouge1_fmeasure_stderr": 0.0021169320380915397, "rouge1_precision": 0.4079186719686208, "rouge1_precision_stderr": 0.0030636128374210455, "rouge1_recall": 0.34551384483174236, "rouge1_recall_stderr": 0.0024411037115400777, "rouge2_fmeasure": 0.13899954079181534, "rouge2_fmeasure_stderr": 0.0016519779895088726, "rouge2_precision": 0.1651169143111655, "rouge2_precision_stderr": 0.0022498261971629634, "rouge2_recall": 0.13570208053691146, "rouge2_recall_stderr": 0.0017306096236515535, "rougeL_fmeasure": 0.26611116257409023, "rougeL_fmeasure_stderr": 0.0017655608447914495, "rougeL_precision": 0.3103180907026251, "rougeL_precision_stderr": 0.0026794184035727514, "rougeL_recall": 0.260674271635608, "rougeL_recall_stderr": 0.0019926530246205786, "rougeLsum_fmeasure": 0.29700738879576205, "rougeLsum_fmeasure_stderr": 0.0019763199856062843, "rougeLsum_precision": 0.34494793963685744, "rougeLsum_precision_stderr": 0.002867601551740783, "rougeLsum_recall": 0.290738713102737, "rougeLsum_recall_stderr": 0.0022139980383301975}, "generate_gramatically_correct_text": {"bleu": 7.664142184014725, "bleu_stderr": 0.18311227507126876, "rouge1_fmeasure": 0.3315310557370324, "rouge1_fmeasure_stderr": 0.002595366438750264, "rouge1_precision": 0.3746709568888028, "rouge1_precision_stderr": 0.0034292359840454125, "rouge1_recall": 0.3318290086834598, "rouge1_recall_stderr": 0.0028931410590327202, "rouge2_fmeasure": 0.14239753185765971, "rouge2_fmeasure_stderr": 0.0016696513011695726, "rouge2_precision": 0.16260171493807835, "rouge2_precision_stderr": 0.002161100502458248, "rouge2_recall": 0.14326943676270018, "rouge2_recall_stderr": 0.0018229254941988782, "rougeL_fmeasure": 0.25032287278156323, "rougeL_fmeasure_stderr": 0.0018610404732014262, "rougeL_precision": 0.2835816428192323, "rougeL_precision_stderr": 0.0025993635120059306, "rougeL_recall": 0.251337772350117, "rougeL_recall_stderr": 0.0021560416701979584, "rougeLsum_fmeasure": 0.27861256778529525, "rougeLsum_fmeasure_stderr": 0.0022359749139328443, "rougeLsum_precision": 0.31567282011474695, "rougeLsum_precision_stderr": 0.0030093908891570794, "rougeLsum_recall": 0.2786749264473846, "rougeLsum_recall_stderr": 0.0024797369016044467}, "generate_text_restaurant": {"bleu": 7.319824182452319, "bleu_stderr": 0.10193025707807249, "rouge1_fmeasure": 0.353385644913835, "rouge1_fmeasure_stderr": 0.0020821634201849126, "rouge1_precision": 0.44030532087327506, "rouge1_precision_stderr": 0.0031770242292659683, "rouge1_recall": 0.32784942801165234, "rouge1_recall_stderr": 0.0023757237014025534, "rouge2_fmeasure": 0.14603196173656227, "rouge2_fmeasure_stderr": 0.0016877020428632365, "rouge2_precision": 0.18788682322290728, "rouge2_precision_stderr": 0.002464730672599637, "rouge2_recall": 0.13467537191827086, "rouge2_recall_stderr": 0.001690154302772729, "rougeL_fmeasure": 0.27131741619623057, "rougeL_fmeasure_stderr": 0.0017940658157043932, "rougeL_precision": 0.3410417220866126, "rougeL_precision_stderr": 0.0028515279745281513, "rougeL_recall": 0.25124499237542, "rougeL_recall_stderr": 0.001976384646702889, "rougeLsum_fmeasure": 0.298421172979648, "rougeLsum_fmeasure_stderr": 0.0020128816004845508, "rougeLsum_precision": 0.3732999668515814, "rougeLsum_precision_stderr": 0.003040944777908066, "rougeLsum_recall": 0.27656091589535414, "rougeLsum_recall_stderr": 0.002210511819363925}, "text": {"bleu": 7.654080416990873, "bleu_stderr": 0.19571238370874128, "rouge1_fmeasure": 0.35023251954607215, "rouge1_fmeasure_stderr": 0.002029722816220765, "rouge1_precision": 0.4239353949486354, "rouge1_precision_stderr": 0.0031328799053710198, "rouge1_recall": 0.3346884409831521, "rouge1_recall_stderr": 0.00232049776848557, "rouge2_fmeasure": 0.14479391497677302, "rouge2_fmeasure_stderr": 0.0016055061136987026, "rouge2_precision": 0.17998608899131224, "rouge2_precision_stderr": 0.0022646779528023306, "rouge2_recall": 0.1379401661329551, "rouge2_recall_stderr": 0.0016637853565731088, "rougeL_fmeasure": 0.2728400159017183, "rougeL_fmeasure_stderr": 0.0017573515029372963, "rougeL_precision": 0.33239544579609576, "rougeL_precision_stderr": 0.002774448505172659, "rougeL_recall": 0.2607705965299782, "rougeL_recall_stderr": 0.001964723134792992, "rougeLsum_fmeasure": 0.29856008882369317, "rougeLsum_fmeasure_stderr": 0.001949304832193815, "rougeLsum_precision": 0.36254724652343057, "rougeLsum_precision_stderr": 0.0029613989798622157, "rougeLsum_recall": 0.28517595951447855, "rougeLsum_recall_stderr": 0.0021666326647344194}}}, "gem_xsum": {"0": {"DOC_boils_down_to_simple_idea_that": {"bleu": 0.5989061497441678, "bleu_stderr": 0.04560411376477311, "rouge1_fmeasure": 0.12035436857080709, "rouge1_fmeasure_stderr": 0.0020099353839720534, "rouge1_precision": 0.08601322052693357, "rouge1_precision_stderr": 0.001489727730411717, "rouge1_recall": 0.20924410822933326, "rouge1_recall_stderr": 0.0034231335371689518, "rouge2_fmeasure": 0.016871170959750856, "rouge2_fmeasure_stderr": 0.0008961563503630702, "rouge2_precision": 0.01193354789546424, "rouge2_precision_stderr": 0.0006397142671079087, "rouge2_recall": 0.029994300661093865, "rouge2_recall_stderr": 0.001603282064351233, "rougeL_fmeasure": 0.10635833102686837, "rougeL_fmeasure_stderr": 0.0016094140448635636, "rougeL_precision": 0.07594233748050107, "rougeL_precision_stderr": 0.001192403250385716, "rougeL_recall": 0.1855080583745368, "rougeL_recall_stderr": 0.002795393404522018, "rougeLsum_fmeasure": 0.09800348259551175, "rougeLsum_fmeasure_stderr": 0.0016526422289216889, "rougeLsum_precision": 0.06979928841705295, "rougeLsum_precision_stderr": 0.0012075993866203928, "rougeLsum_recall": 0.17170883890703695, "rougeLsum_recall_stderr": 0.0029043246785420388}, "DOC_tldr": {"bleu": 0.6951449410126411, "bleu_stderr": 0.07649685778024824, "rouge1_fmeasure": 0.12304686221145984, "rouge1_fmeasure_stderr": 0.0024384970755190246, "rouge1_precision": 0.08785520812835405, "rouge1_precision_stderr": 0.0017998077566166923, "rouge1_recall": 0.21381700588328337, "rouge1_recall_stderr": 0.004102874678024494, "rouge2_fmeasure": 0.019716305531943378, "rouge2_fmeasure_stderr": 0.0009850886667063586, "rouge2_precision": 0.01396692872396121, "rouge2_precision_stderr": 0.0007089258908322197, "rouge2_recall": 0.03497812070098322, "rouge2_recall_stderr": 0.0017422549858707552, "rougeL_fmeasure": 0.103624513733133, "rougeL_fmeasure_stderr": 0.0018723555859277226, "rougeL_precision": 0.073836479271441, "rougeL_precision_stderr": 0.0013755441288147774, "rougeL_recall": 0.1810860810587385, "rougeL_recall_stderr": 0.0032222426550226036, "rougeLsum_fmeasure": 0.0954563322396712, "rougeLsum_fmeasure_stderr": 0.0019181008675671265, "rougeLsum_precision": 0.06797287037657533, "rougeLsum_precision_stderr": 0.0014074123866873501, "rougeLsum_recall": 0.16720206816344646, "rougeLsum_recall_stderr": 0.0033103712098051024}, "article_DOC_summary": {"bleu": 0.9867298890552224, "bleu_stderr": 0.0636863740857457, "rouge1_fmeasure": 0.1620070178287433, "rouge1_fmeasure_stderr": 0.002441688281448867, "rouge1_precision": 0.1158071847580149, "rouge1_precision_stderr": 0.0018165761216020508, "rouge1_recall": 0.28067020528577075, "rouge1_recall_stderr": 0.004128869715644845, "rouge2_fmeasure": 0.02780910006627101, "rouge2_fmeasure_stderr": 0.001048269259419271, "rouge2_precision": 0.019660583386168388, "rouge2_precision_stderr": 0.000745126629124706, "rouge2_recall": 0.04960567998718761, "rouge2_recall_stderr": 0.0019206822821280743, "rougeL_fmeasure": 0.1259092579196459, "rougeL_fmeasure_stderr": 0.0016674239611603732, "rougeL_precision": 0.08983266681131948, "rougeL_precision_stderr": 0.0012376193912151856, "rougeL_recall": 0.21960260688104757, "rougeL_recall_stderr": 0.0029450533082012067, "rougeLsum_fmeasure": 0.1264703650002751, "rougeLsum_fmeasure_stderr": 0.0019559064654329516, "rougeLsum_precision": 0.09018130758669934, "rougeLsum_precision_stderr": 0.001441468599655175, "rougeLsum_recall": 0.22079158054359857, "rougeLsum_recall_stderr": 0.0034244847154332263}, "summarize_DOC": {"bleu": 0.7657539744351544, "bleu_stderr": 0.05960388643906178, "rouge1_fmeasure": 0.1394877149729816, "rouge1_fmeasure_stderr": 0.0023191928763038917, "rouge1_precision": 0.09959661209849045, "rouge1_precision_stderr": 0.001720794675352159, "rouge1_recall": 0.24296043524964275, "rouge1_recall_stderr": 0.003922924238883301, "rouge2_fmeasure": 0.02216490573223825, "rouge2_fmeasure_stderr": 0.0009754645017508243, "rouge2_precision": 0.015676753241847172, "rouge2_precision_stderr": 0.000696440808966843, "rouge2_recall": 0.03949985958379005, "rouge2_recall_stderr": 0.001763700865011535, "rougeL_fmeasure": 0.11748646473161478, "rougeL_fmeasure_stderr": 0.0017149795760748592, "rougeL_precision": 0.08380837589550291, "rougeL_precision_stderr": 0.0012762456181644143, "rougeL_recall": 0.20538014455763795, "rougeL_recall_stderr": 0.002967340337812102, "rougeLsum_fmeasure": 0.10747916740229993, "rougeLsum_fmeasure_stderr": 0.0018034915409559326, "rougeLsum_precision": 0.07649621759728135, "rougeLsum_precision_stderr": 0.0013213921725338553, "rougeLsum_recall": 0.18872305812070983, "rougeLsum_recall_stderr": 0.0031571885489383726}, "summarize_this_DOC_summary": {"bleu": 0.9053200662535719, "bleu_stderr": 0.08304303167521133, "rouge1_fmeasure": 0.15080495502999547, "rouge1_fmeasure_stderr": 0.0023292636824101256, "rouge1_precision": 0.10766417393148146, "rouge1_precision_stderr": 0.0017247775348159335, "rouge1_recall": 0.26220045752079946, "rouge1_recall_stderr": 0.003975340578476309, "rouge2_fmeasure": 0.02550920276281168, "rouge2_fmeasure_stderr": 0.0010004591177405439, "rouge2_precision": 0.018011700797613012, "rouge2_precision_stderr": 0.0007071056250652039, "rouge2_recall": 0.045671998488902174, "rouge2_recall_stderr": 0.0018504317904469703, "rougeL_fmeasure": 0.12351381489334008, "rougeL_fmeasure_stderr": 0.0016767094669245285, "rougeL_precision": 0.08803820960705872, "rougeL_precision_stderr": 0.0012435040927227102, "rougeL_recall": 0.21591728450361894, "rougeL_recall_stderr": 0.0029447735431074496, "rougeLsum_fmeasure": 0.11739126743954412, "rougeLsum_fmeasure_stderr": 0.0018454058790702413, "rougeLsum_precision": 0.08357513379135657, "rougeLsum_precision_stderr": 0.0013517986553990002, "rougeLsum_recall": 0.20562438203051336, "rougeLsum_recall_stderr": 0.00324355265235417}}, "1": {"DOC_boils_down_to_simple_idea_that": {"bleu": 0.8307325092609459, "bleu_stderr": 0.08101919299614214, "rouge1_fmeasure": 0.14265747670098736, "rouge1_fmeasure_stderr": 0.0022533103077694763, "rouge1_precision": 0.11774017314240483, "rouge1_precision_stderr": 0.0019052567574435065, "rouge1_recall": 0.21726972418847335, "rouge1_recall_stderr": 0.004161648851245577, "rouge2_fmeasure": 0.015898317357067135, "rouge2_fmeasure_stderr": 0.0009292567523827307, "rouge2_precision": 0.012105474988350063, "rouge2_precision_stderr": 0.000710088400602416, "rouge2_recall": 0.026644819771942975, "rouge2_recall_stderr": 0.001646589314669167, "rougeL_fmeasure": 0.10633984941798981, "rougeL_fmeasure_stderr": 0.0015849974450020952, "rougeL_precision": 0.08871947393016015, "rougeL_precision_stderr": 0.0014307460077157546, "rougeL_recall": 0.16050680730614136, "rougeL_recall_stderr": 0.0029158160901583295, "rougeLsum_fmeasure": 0.11432471005231339, "rougeLsum_fmeasure_stderr": 0.0017839300909078509, "rougeLsum_precision": 0.09440999098393471, "rougeLsum_precision_stderr": 0.0015075483157921815, "rougeLsum_recall": 0.1745714923938198, "rougeLsum_recall_stderr": 0.0033720794167318327}, "DOC_tldr": {"bleu": 0.6418362037219415, "bleu_stderr": 0.10975824216647798, "rouge1_fmeasure": 0.13551729087860911, "rouge1_fmeasure_stderr": 0.002244723695600438, "rouge1_precision": 0.12486307177941995, "rouge1_precision_stderr": 0.002333030764269263, "rouge1_recall": 0.17701443524540267, "rouge1_recall_stderr": 0.0035983361097093195, "rouge2_fmeasure": 0.012104885502617603, "rouge2_fmeasure_stderr": 0.0008081822477551506, "rouge2_precision": 0.01080484683339422, "rouge2_precision_stderr": 0.0008615061540764822, "rouge2_recall": 0.01766476395873732, "rouge2_recall_stderr": 0.001206171246859144, "rougeL_fmeasure": 0.10464228517330777, "rougeL_fmeasure_stderr": 0.0016250083581085943, "rougeL_precision": 0.0970099571674389, "rougeL_precision_stderr": 0.0017837861435037988, "rougeL_recall": 0.135913907810521, "rougeL_recall_stderr": 0.002573537485904688, "rougeLsum_fmeasure": 0.10680811423589318, "rougeLsum_fmeasure_stderr": 0.0017423671645419993, "rougeLsum_precision": 0.09870668722966038, "rougeLsum_precision_stderr": 0.001839221923939297, "rougeLsum_recall": 0.13939382706838868, "rougeLsum_recall_stderr": 0.002824716995864924}, "article_DOC_summary": {"bleu": 0.986334549008572, "bleu_stderr": 0.1026134280695105, "rouge1_fmeasure": 0.16460140030448664, "rouge1_fmeasure_stderr": 0.0024490418088823833, "rouge1_precision": 0.12534579534327125, "rouge1_precision_stderr": 0.00193945618548172, "rouge1_recall": 0.27058957289695346, "rouge1_recall_stderr": 0.0043828330597585445, "rouge2_fmeasure": 0.024161160413064688, "rouge2_fmeasure_stderr": 0.0011266352477578854, "rouge2_precision": 0.01759280829959392, "rouge2_precision_stderr": 0.0008355125639125885, "rouge2_recall": 0.04185140008866747, "rouge2_recall_stderr": 0.0019643064430206994, "rougeL_fmeasure": 0.12258268240644458, "rougeL_fmeasure_stderr": 0.0016862279472992232, "rougeL_precision": 0.09368708847755541, "rougeL_precision_stderr": 0.0013943909386695036, "rougeL_recall": 0.2019168442700265, "rougeL_recall_stderr": 0.003109796908751444, "rougeLsum_fmeasure": 0.12964372208686004, "rougeLsum_fmeasure_stderr": 0.0019843558414494125, "rougeLsum_precision": 0.09878883028828475, "rougeLsum_precision_stderr": 0.0015789128996359261, "rougeLsum_recall": 0.21398695995793088, "rougeLsum_recall_stderr": 0.003606717868964285}, "summarize_DOC": {"bleu": 0.9744864699598849, "bleu_stderr": 0.0715803104250675, "rouge1_fmeasure": 0.14786528609926117, "rouge1_fmeasure_stderr": 0.0022472583600236513, "rouge1_precision": 0.10779079125778714, "rouge1_precision_stderr": 0.0017364689097811245, "rouge1_recall": 0.2531343205060018, "rouge1_recall_stderr": 0.003849102811710255, "rouge2_fmeasure": 0.024050432775105567, "rouge2_fmeasure_stderr": 0.0011119514244593799, "rouge2_precision": 0.01717373699792966, "rouge2_precision_stderr": 0.0008086755123805268, "rouge2_recall": 0.04258571346118677, "rouge2_recall_stderr": 0.001990619230673135, "rougeL_fmeasure": 0.11829636533500087, "rougeL_fmeasure_stderr": 0.001646799217950579, "rougeL_precision": 0.08616745994892451, "rougeL_precision_stderr": 0.0012884289488737097, "rougeL_recall": 0.20370042941588284, "rougeL_recall_stderr": 0.002916372748330544, "rougeLsum_fmeasure": 0.11550772215317513, "rougeLsum_fmeasure_stderr": 0.0018112100752252266, "rougeLsum_precision": 0.08416622990633002, "rougeLsum_precision_stderr": 0.0014043090246987175, "rougeLsum_recall": 0.1990339703496491, "rougeLsum_recall_stderr": 0.0031810082266012984}, "summarize_this_DOC_summary": {"bleu": 1.0517549411798284, "bleu_stderr": 0.08869197714127522, "rouge1_fmeasure": 0.16458352372455684, "rouge1_fmeasure_stderr": 0.0024404180174069736, "rouge1_precision": 0.12366225220702332, "rouge1_precision_stderr": 0.0019035992000767568, "rouge1_recall": 0.2746639885726219, "rouge1_recall_stderr": 0.004363644416585785, "rouge2_fmeasure": 0.0254681124378878, "rouge2_fmeasure_stderr": 0.0011760381453017, "rouge2_precision": 0.01831848136320181, "rouge2_precision_stderr": 0.0008613493134626757, "rouge2_recall": 0.044642681354896206, "rouge2_recall_stderr": 0.0020693469381105048, "rougeL_fmeasure": 0.12335078113747294, "rougeL_fmeasure_stderr": 0.0017240156359532798, "rougeL_precision": 0.09283957435911433, "rougeL_precision_stderr": 0.0013633579746673554, "rougeL_recall": 0.20656882824913186, "rougeL_recall_stderr": 0.0031972954373685456, "rougeLsum_fmeasure": 0.12839142485622748, "rougeLsum_fmeasure_stderr": 0.0019623450564247953, "rougeLsum_precision": 0.09649134174288254, "rougeLsum_precision_stderr": 0.0015227636340121218, "rougeLsum_recall": 0.21532151284750878, "rougeLsum_recall_stderr": 0.0035949140524341836}}, "2": {"DOC_boils_down_to_simple_idea_that": {"bleu": 0.7096901242580976, "bleu_stderr": 0.05577067558873664, "rouge1_fmeasure": 0.1481415675239767, "rouge1_fmeasure_stderr": 0.0021642331088208224, "rouge1_precision": 0.11302706654940622, "rouge1_precision_stderr": 0.0018593332628316893, "rouge1_recall": 0.2460436363471978, "rouge1_recall_stderr": 0.0037872620423532104, "rouge2_fmeasure": 0.0174749223761466, "rouge2_fmeasure_stderr": 0.000900127336792311, "rouge2_precision": 0.013053642716381332, "rouge2_precision_stderr": 0.0007155352294008017, "rouge2_recall": 0.03017269382059932, "rouge2_recall_stderr": 0.0015996985516903391, "rougeL_fmeasure": 0.1080255694309031, "rougeL_fmeasure_stderr": 0.0014919817019001394, "rougeL_precision": 0.08299048940700292, "rougeL_precision_stderr": 0.0014081479474376902, "rougeL_recall": 0.17954598888703394, "rougeL_recall_stderr": 0.0026498882602493264, "rougeLsum_fmeasure": 0.11778050548494788, "rougeLsum_fmeasure_stderr": 0.0017160843639228713, "rougeLsum_precision": 0.08995434230427667, "rougeLsum_precision_stderr": 0.0015144673716852113, "rougeLsum_recall": 0.19646935910004223, "rougeLsum_recall_stderr": 0.0030868956085950226}, "DOC_tldr": {"bleu": 0.8108179139657711, "bleu_stderr": 0.12705995346927912, "rouge1_fmeasure": 0.14570650267756477, "rouge1_fmeasure_stderr": 0.002378941385995561, "rouge1_precision": 0.13693727131284883, "rouge1_precision_stderr": 0.002867447164210865, "rouge1_recall": 0.1925058409582237, "rouge1_recall_stderr": 0.00344213336972596, "rouge2_fmeasure": 0.016540998688253494, "rouge2_fmeasure_stderr": 0.0010166295676320167, "rouge2_precision": 0.015417250842210722, "rouge2_precision_stderr": 0.001067355594423882, "rouge2_recall": 0.02339412063589744, "rouge2_recall_stderr": 0.0015128675685687942, "rougeL_fmeasure": 0.11612824174493956, "rougeL_fmeasure_stderr": 0.0018217319112931597, "rougeL_precision": 0.1092349946394738, "rougeL_precision_stderr": 0.0022921046872309246, "rougeL_recall": 0.15434494177372146, "rougeL_recall_stderr": 0.0026589145886085404, "rougeLsum_fmeasure": 0.11514154801275071, "rougeLsum_fmeasure_stderr": 0.0018878468117351512, "rougeLsum_precision": 0.10856158470399667, "rougeLsum_precision_stderr": 0.0023269612772477415, "rougeLsum_recall": 0.152553343173584, "rougeLsum_recall_stderr": 0.0027788394482328844}, "article_DOC_summary": {"bleu": 0.8510392504395363, "bleu_stderr": 0.06647941816704432, "rouge1_fmeasure": 0.15079272411614866, "rouge1_fmeasure_stderr": 0.0024454125650679305, "rouge1_precision": 0.11833601279755995, "rouge1_precision_stderr": 0.002199294284784323, "rouge1_recall": 0.24121068192166684, "rouge1_recall_stderr": 0.004044710436865143, "rouge2_fmeasure": 0.021955967558594934, "rouge2_fmeasure_stderr": 0.001087239850414522, "rouge2_precision": 0.016827094361182786, "rouge2_precision_stderr": 0.0008831709899277623, "rouge2_recall": 0.036633244517976074, "rouge2_recall_stderr": 0.0018506466619519948, "rougeL_fmeasure": 0.11723212187021603, "rougeL_fmeasure_stderr": 0.001714077795522329, "rougeL_precision": 0.09217477971271017, "rougeL_precision_stderr": 0.0016246776666746755, "rougeL_recall": 0.18812387120682225, "rougeL_recall_stderr": 0.002891644059806244, "rougeLsum_fmeasure": 0.1185738466895609, "rougeLsum_fmeasure_stderr": 0.0019372106823996678, "rougeLsum_precision": 0.09310810494075238, "rougeLsum_precision_stderr": 0.001750123872504354, "rougeLsum_recall": 0.1906145778565124, "rougeLsum_recall_stderr": 0.00328348190414569}, "summarize_DOC": {"bleu": 0.8347136741256534, "bleu_stderr": 0.062076277683922425, "rouge1_fmeasure": 0.13806182767970213, "rouge1_fmeasure_stderr": 0.0021135695098749214, "rouge1_precision": 0.09974253383196298, "rouge1_precision_stderr": 0.0016508496308147503, "rouge1_recall": 0.24044895366223354, "rouge1_recall_stderr": 0.003610084224116856, "rouge2_fmeasure": 0.021850132907452764, "rouge2_fmeasure_stderr": 0.001062000791042869, "rouge2_precision": 0.015474430089813513, "rouge2_precision_stderr": 0.000760295961817625, "rouge2_recall": 0.0390759843386084, "rouge2_recall_stderr": 0.0019080665242204116, "rougeL_fmeasure": 0.11603612234525328, "rougeL_fmeasure_stderr": 0.0016404618326966145, "rougeL_precision": 0.08367374656252795, "rougeL_precision_stderr": 0.0012812689380292408, "rougeL_recall": 0.20304267063542045, "rougeL_recall_stderr": 0.0028755638811545294, "rougeLsum_fmeasure": 0.10727262095783592, "rougeLsum_fmeasure_stderr": 0.0016997810733515313, "rougeLsum_precision": 0.07733059958801149, "rougeLsum_precision_stderr": 0.0013169092247786304, "rougeLsum_recall": 0.1882421408340462, "rougeLsum_recall_stderr": 0.0029988980863709493}, "summarize_this_DOC_summary": {"bleu": 0.9359180990331135, "bleu_stderr": 0.097313852367643, "rouge1_fmeasure": 0.1489043126868222, "rouge1_fmeasure_stderr": 0.002414057619883924, "rouge1_precision": 0.11477590393567126, "rouge1_precision_stderr": 0.002116330005854684, "rouge1_recall": 0.24394235435709302, "rouge1_recall_stderr": 0.004069202937893897, "rouge2_fmeasure": 0.02344635398091455, "rouge2_fmeasure_stderr": 0.0011875761392866745, "rouge2_precision": 0.017617469606827755, "rouge2_precision_stderr": 0.0009209461630191176, "rouge2_recall": 0.039942432060720914, "rouge2_recall_stderr": 0.0020431563227289234, "rougeL_fmeasure": 0.11876289392440431, "rougeL_fmeasure_stderr": 0.0017958651709665465, "rougeL_precision": 0.09141125984419861, "rougeL_precision_stderr": 0.0016082349170530377, "rougeL_recall": 0.1955280825356397, "rougeL_recall_stderr": 0.0030928571079126945, "rougeLsum_fmeasure": 0.11666161719412536, "rougeLsum_fmeasure_stderr": 0.0019395954814823589, "rougeLsum_precision": 0.08991259226184872, "rougeLsum_precision_stderr": 0.0017045288942889236, "rougeLsum_recall": 0.1921527798348713, "rougeLsum_recall_stderr": 0.003343896055475177}}, "3": {"DOC_boils_down_to_simple_idea_that": {"bleu": 0.7643563196224507, "bleu_stderr": 0.060516055001859886, "rouge1_fmeasure": 0.13993184120346575, "rouge1_fmeasure_stderr": 0.002395620259341809, "rouge1_precision": 0.10499197275901183, "rouge1_precision_stderr": 0.0019010472325354404, "rouge1_recall": 0.23424489218202285, "rouge1_recall_stderr": 0.004151663117206758, "rouge2_fmeasure": 0.01773853594640338, "rouge2_fmeasure_stderr": 0.0009780501520640062, "rouge2_precision": 0.013013272243975858, "rouge2_precision_stderr": 0.0007437340426547505, "rouge2_recall": 0.030512183916105506, "rouge2_recall_stderr": 0.0016971799846190242, "rougeL_fmeasure": 0.10336085541455355, "rougeL_fmeasure_stderr": 0.0016861984554507592, "rougeL_precision": 0.07787068629627976, "rougeL_precision_stderr": 0.0013947978353617287, "rougeL_recall": 0.17322899854212984, "rougeL_recall_stderr": 0.0029625614134759564, "rougeLsum_fmeasure": 0.11170901074459809, "rougeLsum_fmeasure_stderr": 0.001935231182288914, "rougeLsum_precision": 0.08385124269644273, "rougeLsum_precision_stderr": 0.0015454338092998716, "rougeLsum_recall": 0.1877925759738355, "rougeLsum_recall_stderr": 0.0034402617687262706}, "DOC_tldr": {"bleu": 0.8773649045212694, "bleu_stderr": 0.11660132941903724, "rouge1_fmeasure": 0.1426531931541618, "rouge1_fmeasure_stderr": 0.002586850906713085, "rouge1_precision": 0.13563786026465277, "rouge1_precision_stderr": 0.0030566129634817477, "rouge1_recall": 0.18802799291524244, "rouge1_recall_stderr": 0.00357664038215709, "rouge2_fmeasure": 0.01889574180325777, "rouge2_fmeasure_stderr": 0.0010911361599695013, "rouge2_precision": 0.017442792260430814, "rouge2_precision_stderr": 0.001100826746094403, "rouge2_recall": 0.026449724957200424, "rouge2_recall_stderr": 0.0015566681933243279, "rougeL_fmeasure": 0.1139215911001409, "rougeL_fmeasure_stderr": 0.0019571989970646572, "rougeL_precision": 0.1079022009981362, "rougeL_precision_stderr": 0.002335404534765411, "rougeL_recall": 0.15167890991580765, "rougeL_recall_stderr": 0.0028008093319595393, "rougeLsum_fmeasure": 0.11339280362226653, "rougeLsum_fmeasure_stderr": 0.0020325791985732135, "rougeLsum_precision": 0.10782682350987516, "rougeLsum_precision_stderr": 0.0024013803164332965, "rougeLsum_recall": 0.15026311614000185, "rougeLsum_recall_stderr": 0.0028973161396880012}, "article_DOC_summary": {"bleu": 0.8650437116316979, "bleu_stderr": 0.08348862368049724, "rouge1_fmeasure": 0.14375568998105198, "rouge1_fmeasure_stderr": 0.002550732075823139, "rouge1_precision": 0.11511064720378139, "rouge1_precision_stderr": 0.0024031770641084484, "rouge1_recall": 0.22827150593652096, "rouge1_recall_stderr": 0.00416286720206103, "rouge2_fmeasure": 0.020853724585447975, "rouge2_fmeasure_stderr": 0.0011315789722664176, "rouge2_precision": 0.016386126450038938, "rouge2_precision_stderr": 0.0009430306754946043, "rouge2_recall": 0.03453203803155488, "rouge2_recall_stderr": 0.0018851772654117098, "rougeL_fmeasure": 0.11360197423806047, "rougeL_fmeasure_stderr": 0.001884854751254693, "rougeL_precision": 0.09095045508362522, "rougeL_precision_stderr": 0.0018411782290517719, "rougeL_recall": 0.18142579882700435, "rougeL_recall_stderr": 0.0031425768784492493, "rougeLsum_fmeasure": 0.11426161274403947, "rougeLsum_fmeasure_stderr": 0.002072690651007159, "rougeLsum_precision": 0.09156035684290141, "rougeLsum_precision_stderr": 0.00196609095636847, "rougeLsum_recall": 0.18238021901307033, "rougeLsum_recall_stderr": 0.0034503657802804075}, "summarize_DOC": {"bleu": 0.8124291106760078, "bleu_stderr": 0.07588482930693484, "rouge1_fmeasure": 0.13115011437349358, "rouge1_fmeasure_stderr": 0.002301574585288779, "rouge1_precision": 0.09689033249970055, "rouge1_precision_stderr": 0.0018810183346657067, "rouge1_recall": 0.2240723175463038, "rouge1_recall_stderr": 0.003898850764408054, "rouge2_fmeasure": 0.020384730084258812, "rouge2_fmeasure_stderr": 0.001038756802634804, "rouge2_precision": 0.014805074825435426, "rouge2_precision_stderr": 0.0007813933511829814, "rouge2_recall": 0.035775335550481645, "rouge2_recall_stderr": 0.0018150201824477363, "rougeL_fmeasure": 0.11089421988144217, "rougeL_fmeasure_stderr": 0.0018199727364072546, "rougeL_precision": 0.08180231716848364, "rougeL_precision_stderr": 0.001509999290109991, "rougeL_recall": 0.19020520762940066, "rougeL_recall_stderr": 0.003130840716495653, "rougeLsum_fmeasure": 0.10193009295990486, "rougeLsum_fmeasure_stderr": 0.0018015834348326844, "rougeLsum_precision": 0.07516233715156442, "rougeLsum_precision_stderr": 0.0014943501606461884, "rougeLsum_recall": 0.17573853870134074, "rougeLsum_recall_stderr": 0.0031552844726888797}, "summarize_this_DOC_summary": {"bleu": 0.8545144299660299, "bleu_stderr": 0.08062058614293066, "rouge1_fmeasure": 0.14143975183431184, "rouge1_fmeasure_stderr": 0.002624919098315165, "rouge1_precision": 0.10967477103152969, "rouge1_precision_stderr": 0.002373361239237867, "rouge1_recall": 0.22921698427745044, "rouge1_recall_stderr": 0.004179760492319134, "rouge2_fmeasure": 0.021683379341115812, "rouge2_fmeasure_stderr": 0.0011414403236527958, "rouge2_precision": 0.01649113601256011, "rouge2_precision_stderr": 0.0009108210651028919, "rouge2_recall": 0.03621079704469094, "rouge2_recall_stderr": 0.0019138662731944262, "rougeL_fmeasure": 0.11452190311765521, "rougeL_fmeasure_stderr": 0.0019555924223011788, "rougeL_precision": 0.08842314517868648, "rougeL_precision_stderr": 0.0017879328745720076, "rougeL_recall": 0.18710793878265647, "rougeL_recall_stderr": 0.003197890711089028, "rougeLsum_fmeasure": 0.1108174940054984, "rougeLsum_fmeasure_stderr": 0.002093506046561213, "rougeLsum_precision": 0.08585520766581471, "rougeLsum_precision_stderr": 0.0018884567405713097, "rougeLsum_recall": 0.1806032948250851, "rougeLsum_recall_stderr": 0.003410584937322093}}, "4": {"DOC_boils_down_to_simple_idea_that": {"bleu": 0.29936737554664894, "bleu_stderr": 0.06333594224392126, "rouge1_fmeasure": 0.034205133663320925, "rouge1_fmeasure_stderr": 0.002130522101860963, "rouge1_precision": 0.029270950352660315, "rouge1_precision_stderr": 0.0020065508927545363, "rouge1_recall": 0.054292494387326445, "rouge1_recall_stderr": 0.0035095105726254796, "rouge2_fmeasure": 0.004783264838725394, "rouge2_fmeasure_stderr": 0.0006044566237329345, "rouge2_precision": 0.004080736859560897, "rouge2_precision_stderr": 0.0005900878496520041, "rouge2_recall": 0.007641895050367479, "rouge2_recall_stderr": 0.00097223815465809, "rougeL_fmeasure": 0.025477711600550405, "rougeL_fmeasure_stderr": 0.0015794541340020175, "rougeL_precision": 0.022370274339247025, "rougeL_precision_stderr": 0.001625959107979613, "rougeL_recall": 0.04008109112128974, "rougeL_recall_stderr": 0.0025643726913754435, "rougeLsum_fmeasure": 0.027411630968536074, "rougeLsum_fmeasure_stderr": 0.0017286334063830189, "rougeLsum_precision": 0.023817663907487817, "rougeLsum_precision_stderr": 0.0017123315453502917, "rougeLsum_recall": 0.04362025506139685, "rougeLsum_recall_stderr": 0.002869716532881049}, "DOC_tldr": {"bleu": 0.22273027127435427, "bleu_stderr": 0.053862193531175, "rouge1_fmeasure": 0.040147604598473816, "rouge1_fmeasure_stderr": 0.002480690262574129, "rouge1_precision": 0.04056265174869925, "rouge1_precision_stderr": 0.0027356110529654534, "rouge1_recall": 0.050786036823568484, "rouge1_recall_stderr": 0.003196010331614339, "rouge2_fmeasure": 0.006640579605150196, "rouge2_fmeasure_stderr": 0.0009022022003023071, "rouge2_precision": 0.006607559048731122, "rouge2_precision_stderr": 0.001009742810903406, "rouge2_recall": 0.00849924754298773, "rouge2_recall_stderr": 0.0010791020860047476, "rougeL_fmeasure": 0.032413930700901525, "rougeL_fmeasure_stderr": 0.0019512957708450456, "rougeL_precision": 0.03310929259525501, "rougeL_precision_stderr": 0.002243362243706627, "rougeL_recall": 0.04113526678175656, "rougeL_recall_stderr": 0.002542893900861329, "rougeLsum_fmeasure": 0.032497622810383237, "rougeLsum_fmeasure_stderr": 0.001977165308187117, "rougeLsum_precision": 0.033227844625563996, "rougeLsum_precision_stderr": 0.0022608759002654445, "rougeLsum_recall": 0.04106024416303349, "rougeLsum_recall_stderr": 0.0025628565510947927}, "article_DOC_summary": {"bleu": 0.41795248569633103, "bleu_stderr": 0.084171862077561, "rouge1_fmeasure": 0.03860671254711545, "rouge1_fmeasure_stderr": 0.0022900584510195322, "rouge1_precision": 0.0361602458825991, "rouge1_precision_stderr": 0.0025988245241512615, "rouge1_recall": 0.0581275939105786, "rouge1_recall_stderr": 0.0035711432213003467, "rouge2_fmeasure": 0.006231843463345877, "rouge2_fmeasure_stderr": 0.0007012509924568781, "rouge2_precision": 0.005992076983678361, "rouge2_precision_stderr": 0.0011155187418557422, "rouge2_recall": 0.009962165254990031, "rouge2_recall_stderr": 0.0011307954713829275, "rougeL_fmeasure": 0.031530683354832556, "rougeL_fmeasure_stderr": 0.0018296711578288528, "rougeL_precision": 0.03038144486746073, "rougeL_precision_stderr": 0.0023281897845746865, "rougeL_recall": 0.04731308569695526, "rougeL_recall_stderr": 0.0028495942670980546, "rougeLsum_fmeasure": 0.03178346574583942, "rougeLsum_fmeasure_stderr": 0.001898518321849197, "rougeLsum_precision": 0.030582547849958886, "rougeLsum_precision_stderr": 0.002360088780868479, "rougeLsum_recall": 0.047711987788717505, "rougeLsum_recall_stderr": 0.002969080473622203}, "summarize_DOC": {"bleu": 0.5188346596881508, "bleu_stderr": 0.1162647822321323, "rouge1_fmeasure": 0.03985059812853305, "rouge1_fmeasure_stderr": 0.0022760105727489804, "rouge1_precision": 0.03575664714500481, "rouge1_precision_stderr": 0.0024098528232116526, "rouge1_recall": 0.060819442484463054, "rouge1_recall_stderr": 0.003534881031726274, "rouge2_fmeasure": 0.007018029042731219, "rouge2_fmeasure_stderr": 0.000685007347774824, "rouge2_precision": 0.005750259558436412, "rouge2_precision_stderr": 0.0006358449659266129, "rouge2_recall": 0.011282915311051312, "rouge2_recall_stderr": 0.0011299755593093203, "rougeL_fmeasure": 0.032959125867263926, "rougeL_fmeasure_stderr": 0.001860506762679618, "rougeL_precision": 0.030116615236100916, "rougeL_precision_stderr": 0.0021214097977901845, "rougeL_recall": 0.05019883302718781, "rougeL_recall_stderr": 0.0028798226137028322, "rougeLsum_fmeasure": 0.032337968793062846, "rougeLsum_fmeasure_stderr": 0.0018663100809540166, "rougeLsum_precision": 0.02960913737630851, "rougeLsum_precision_stderr": 0.0021194541107393936, "rougeLsum_recall": 0.049340056932530726, "rougeLsum_recall_stderr": 0.0029147509307593054}, "summarize_this_DOC_summary": {"bleu": 0.41550983722811713, "bleu_stderr": 0.11383336021662172, "rouge1_fmeasure": 0.037197403374487924, "rouge1_fmeasure_stderr": 0.0022954634096379305, "rouge1_precision": 0.033523252947635904, "rouge1_precision_stderr": 0.002262808835339776, "rouge1_recall": 0.05524121400042497, "rouge1_recall_stderr": 0.003532082798269108, "rouge2_fmeasure": 0.006054078203169595, "rouge2_fmeasure_stderr": 0.0007863768658417492, "rouge2_precision": 0.0051584458678752216, "rouge2_precision_stderr": 0.0007026116069116543, "rouge2_recall": 0.009635922855585887, "rouge2_recall_stderr": 0.0012421025115398562, "rougeL_fmeasure": 0.030859284839692826, "rougeL_fmeasure_stderr": 0.0019074776816356488, "rougeL_precision": 0.028324453021289078, "rougeL_precision_stderr": 0.001994218364384606, "rougeL_recall": 0.045582045072611516, "rougeL_recall_stderr": 0.0028859350433643343, "rougeLsum_fmeasure": 0.030639007644487726, "rougeLsum_fmeasure_stderr": 0.0019336596995026226, "rougeLsum_precision": 0.028190743604595166, "rougeLsum_precision_stderr": 0.0020193479074785987, "rougeLsum_recall": 0.04530859399363896, "rougeLsum_recall_stderr": 0.0029471761234043025}}, "5": {"DOC_boils_down_to_simple_idea_that": {"bleu": 0.0, "bleu_stderr": 0.0, "rouge1_fmeasure": 6.125949522175937e-05, "rouge1_fmeasure_stderr": 6.125949522176127e-05, "rouge1_precision": 0.0008576329331046312, "rouge1_precision_stderr": 0.0008576329331046343, "rouge1_recall": 3.1764182707578934e-05, "rouge1_recall_stderr": 3.176418270757912e-05, "rouge2_fmeasure": 0.0, "rouge2_fmeasure_stderr": 0.0, "rouge2_precision": 0.0, "rouge2_precision_stderr": 0.0, "rouge2_recall": 0.0, "rouge2_recall_stderr": 0.0, "rougeL_fmeasure": 6.125949522175937e-05, "rougeL_fmeasure_stderr": 6.125949522176127e-05, "rougeL_precision": 0.0008576329331046312, "rougeL_precision_stderr": 0.0008576329331046343, "rougeL_recall": 3.1764182707578934e-05, "rougeL_recall_stderr": 3.176418270757912e-05, "rougeLsum_fmeasure": 6.125949522175937e-05, "rougeLsum_fmeasure_stderr": 6.125949522176127e-05, "rougeLsum_precision": 0.0008576329331046312, "rougeLsum_precision_stderr": 0.0008576329331046343, "rougeLsum_recall": 3.1764182707578934e-05, "rougeLsum_recall_stderr": 3.176418270757912e-05}, "DOC_tldr": {"bleu": 1.1827594679031042e-43, "bleu_stderr": 4.377910669778258e-37, "rouge1_fmeasure": 0.002408518357660293, "rouge1_fmeasure_stderr": 0.0006851091594038417, "rouge1_precision": 0.0028264204041118578, "rouge1_precision_stderr": 0.0008349091404664074, "rouge1_recall": 0.002169808352873373, "rouge1_recall_stderr": 0.0006083551170636029, "rouge2_fmeasure": 0.0002397463551736582, "rouge2_fmeasure_stderr": 0.00013033009573483993, "rouge2_precision": 0.00029254180891250816, "rouge2_precision_stderr": 0.00015725543023099734, "rouge2_recall": 0.00020462820860040322, "rouge2_recall_stderr": 0.00011211479804596237, "rougeL_fmeasure": 0.0017660754927783585, "rougeL_fmeasure_stderr": 0.00047012290492895134, "rougeL_precision": 0.0020221693154545543, "rougeL_precision_stderr": 0.0005384638968072176, "rougeL_recall": 0.0016282149852303604, "rougeL_recall_stderr": 0.0004451035213829608, "rougeLsum_fmeasure": 0.0018882985436314338, "rougeLsum_fmeasure_stderr": 0.0005141685685603013, "rougeLsum_precision": 0.00218432680280627, "rougeLsum_precision_stderr": 0.0006054710624941614, "rougeLsum_recall": 0.001726345399206282, "rougeLsum_recall_stderr": 0.00047538249577709987}, "article_DOC_summary": {"bleu": 8.059349929930117e-40, "bleu_stderr": 3.4078462014416495e-34, "rouge1_fmeasure": 0.002527603190035361, "rouge1_fmeasure_stderr": 0.00068757084609251, "rouge1_precision": 0.00282366128721056, "rouge1_precision_stderr": 0.0007697832157484954, "rouge1_recall": 0.002365813329267624, "rouge1_recall_stderr": 0.0006488826359222657, "rouge2_fmeasure": 0.00020969228861543636, "rouge2_fmeasure_stderr": 9.41768743666813e-05, "rouge2_precision": 0.000252945660825794, "rouge2_precision_stderr": 0.0001130835622425815, "rouge2_recall": 0.0001820087669144273, "rouge2_recall_stderr": 8.275145912995973e-05, "rougeL_fmeasure": 0.0018180833551753694, "rougeL_fmeasure_stderr": 0.0004787735421768299, "rougeL_precision": 0.0020324491777993737, "rougeL_precision_stderr": 0.0005401952082914505, "rougeL_recall": 0.001705553553343957, "rougeL_recall_stderr": 0.00045030351383285445, "rougeLsum_fmeasure": 0.0019064161369800514, "rougeLsum_fmeasure_stderr": 0.0005036949386606113, "rougeLsum_precision": 0.002125879390906554, "rougeLsum_precision_stderr": 0.0005641336556569049, "rougeLsum_recall": 0.0017893614930695643, "rougeLsum_recall_stderr": 0.0004747147768544628}, "summarize_DOC": {"bleu": 6.894559936640943e-38, "bleu_stderr": 5.078171225423703e-32, "rouge1_fmeasure": 0.00257629662639923, "rouge1_fmeasure_stderr": 0.0007584585077324427, "rouge1_precision": 0.0027970449110702633, "rouge1_precision_stderr": 0.0008129954674738013, "rouge1_recall": 0.0024652900122106723, "rouge1_recall_stderr": 0.0007379988663176068, "rouge2_fmeasure": 0.00027004452530749476, "rouge2_fmeasure_stderr": 0.00018148779778783585, "rouge2_precision": 0.000261704167087075, "rouge2_precision_stderr": 0.00017583118303625035, "rouge2_recall": 0.00027915111155954665, "rouge2_recall_stderr": 0.0001876136151566084, "rougeL_fmeasure": 0.002111652191363848, "rougeL_fmeasure_stderr": 0.0005941763033496732, "rougeL_precision": 0.002311528640826497, "rougeL_precision_stderr": 0.0006531263217620076, "rougeL_recall": 0.0020110161874394208, "rougeL_recall_stderr": 0.0005684052414990399, "rougeLsum_fmeasure": 0.002214671104382056, "rougeLsum_fmeasure_stderr": 0.0006380204218087325, "rougeLsum_precision": 0.002412426632956454, "rougeLsum_precision_stderr": 0.0006907319147059392, "rougeLsum_recall": 0.002115676852444913, "rougeLsum_recall_stderr": 0.0006160449658742334}, "summarize_this_DOC_summary": {"bleu": 0.0, "bleu_stderr": 0.0, "rouge1_fmeasure": 0.000708246579679391, "rouge1_fmeasure_stderr": 0.00023949778866834165, "rouge1_precision": 0.0031446540880503146, "rouge1_precision_stderr": 0.0010851526656093654, "rouge1_recall": 0.0004018246904679879, "rouge1_recall_stderr": 0.0001360401158331796, "rouge2_fmeasure": 5.360205831903945e-05, "rouge2_fmeasure_stderr": 5.3602058319039565e-05, "rouge2_precision": 0.0004288164665523156, "rouge2_precision_stderr": 0.0004288164665523165, "rouge2_recall": 2.858776443682104e-05, "rouge2_recall_stderr": 2.8587764436821168e-05, "rougeL_fmeasure": 0.000708246579679391, "rougeL_fmeasure_stderr": 0.00023949778866834165, "rougeL_precision": 0.0031446540880503146, "rougeL_precision_stderr": 0.0010851526656093654, "rougeL_recall": 0.0004018246904679879, "rougeL_recall_stderr": 0.0001360401158331796, "rougeLsum_fmeasure": 0.000708246579679391, "rougeLsum_fmeasure_stderr": 0.00023949778866834165, "rougeLsum_precision": 0.0031446540880503146, "rougeLsum_precision_stderr": 0.0010851526656093654, "rougeLsum_recall": 0.0004018246904679879, "rougeLsum_recall_stderr": 0.0001360401158331796}}}, "piqa": {"0": {"Correct the solution": {"bleu": 5.044003528820165, "bleu_stderr": 0.22920626380593712, "rouge1_fmeasure": 0.13070246265270175, "rouge1_fmeasure_stderr": 0.003003328865094663, "rouge1_precision": 0.08223335503910409, "rouge1_precision_stderr": 0.0024516571009502493, "rouge1_recall": 0.6043317835131486, "rouge1_recall_stderr": 0.007310140932058555, "rouge2_fmeasure": 0.09519041983155013, "rouge2_fmeasure_stderr": 0.002905103095548517, "rouge2_precision": 0.06021814295664582, "rouge2_precision_stderr": 0.002303597081892545, "rouge2_recall": 0.44232864311481884, "rouge2_recall_stderr": 0.008135472118435535, "rougeL_fmeasure": 0.1270728154104261, "rougeL_fmeasure_stderr": 0.0029857125025585436, "rougeL_precision": 0.07970090960055028, "rougeL_precision_stderr": 0.002390776645143582, "rougeL_recall": 0.5915829369519617, "rougeL_recall_stderr": 0.007434090945267709, "rougeLsum_fmeasure": 0.125629974165267, "rougeLsum_fmeasure_stderr": 0.002984884476068228, "rougeLsum_precision": 0.07898279807795379, "rougeLsum_precision_stderr": 0.0024089195054829956, "rougeLsum_recall": 0.5841163781141749, "rougeLsum_recall_stderr": 0.00745835270564824}, "choose the most appropriate solution": {"acc": 0.49075081610446136, "acc_norm": 0.49075081610446136, "acc_norm_stderr": 0.011663828032649183, "acc_stderr": 0.011663828032649183}, "no prompt needed": {"bleu": 0.08644025412923256, "bleu_stderr": 0.009820950909340235, "rouge1_fmeasure": 0.031036089835208214, "rouge1_fmeasure_stderr": 0.0009813521147527423, "rouge1_precision": 0.022663125514556327, "rouge1_precision_stderr": 0.0013513829670530827, "rouge1_recall": 0.1592144653136851, "rouge1_recall_stderr": 0.003449871907818082, "rouge2_fmeasure": 0.004256247232539841, "rouge2_fmeasure_stderr": 0.00034400170235730353, "rouge2_precision": 0.003241010643234634, "rouge2_precision_stderr": 0.0004333769961243567, "rouge2_recall": 0.021524339394750014, "rouge2_recall_stderr": 0.0013450358010657275, "rougeL_fmeasure": 0.028702267430638435, "rougeL_fmeasure_stderr": 0.0009058455781743254, "rougeL_precision": 0.020762352004530072, "rougeL_precision_stderr": 0.0012497895941737545, "rougeL_recall": 0.1502718739661574, "rougeL_recall_stderr": 0.003305027485971818, "rougeLsum_fmeasure": 0.025974232921307155, "rougeLsum_fmeasure_stderr": 0.0008611143023707996, "rougeLsum_precision": 0.01933761544810985, "rougeLsum_precision_stderr": 0.0012600611343390243, "rougeLsum_recall": 0.1362003183642396, "rougeLsum_recall_stderr": 0.00300408432276789}, "pick_correct_choice_index": {"acc": 0.49510337323177367, "acc_norm": 0.49510337323177367, "acc_norm_stderr": 0.01166526473007815, "acc_stderr": 0.01166526473007815}, "what_is_the_correct_ending": {"acc": 0.5233949945593036, "acc_norm": 0.5250272034820457, "acc_norm_stderr": 0.011651200967623706, "acc_stderr": 0.01165304715592779}}, "1": {"Correct the solution": {"bleu": 10.987284589298396, "bleu_stderr": 0.6228982805404496, "rouge1_fmeasure": 0.27365913419935356, "rouge1_fmeasure_stderr": 0.007178789576035563, "rouge1_precision": 0.3018921785857166, "rouge1_precision_stderr": 0.007592424912559347, "rouge1_recall": 0.34032411186465444, "rouge1_recall_stderr": 0.007665397277299667, "rouge2_fmeasure": 0.1734691615853129, "rouge2_fmeasure_stderr": 0.006761885716826925, "rouge2_precision": 0.182995294256973, "rouge2_precision_stderr": 0.007121557687340213, "rouge2_recall": 0.2131172886544418, "rouge2_recall_stderr": 0.0073735162438965775, "rougeL_fmeasure": 0.2617978649064106, "rougeL_fmeasure_stderr": 0.00719744805064835, "rougeL_precision": 0.2866580016638699, "rougeL_precision_stderr": 0.007545348452121212, "rougeL_recall": 0.3272517692490847, "rougeL_recall_stderr": 0.007719965820540302, "rougeLsum_fmeasure": 0.26419466018780496, "rougeLsum_fmeasure_stderr": 0.007189020162760364, "rougeLsum_precision": 0.29054400425577176, "rougeLsum_precision_stderr": 0.007575454546327207, "rougeLsum_recall": 0.3290770238121191, "rougeLsum_recall_stderr": 0.007681543530250764}, "choose the most appropriate solution": {"acc": 0.5021762785636561, "acc_norm": 0.5021762785636561, "acc_norm_stderr": 0.011665713661738877, "acc_stderr": 0.011665713661738877}, "no prompt needed": {"bleu": 0.14304039520961487, "bleu_stderr": 0.020196407881148105, "rouge1_fmeasure": 0.04722334546545548, "rouge1_fmeasure_stderr": 0.0020880436511264647, "rouge1_precision": 0.053711187417481356, "rouge1_precision_stderr": 0.0029279067285896583, "rouge1_recall": 0.09582097083032212, "rouge1_recall_stderr": 0.00324411522349448, "rouge2_fmeasure": 0.007609013308850757, "rouge2_fmeasure_stderr": 0.0006822487640430323, "rouge2_precision": 0.009321490289307479, "rouge2_precision_stderr": 0.000928495984049966, "rouge2_recall": 0.013837525790323843, "rouge2_recall_stderr": 0.0011119759768626336, "rougeL_fmeasure": 0.04129383170227979, "rougeL_fmeasure_stderr": 0.0018149259520630428, "rougeL_precision": 0.04649502848369309, "rougeL_precision_stderr": 0.00254016005961217, "rougeL_recall": 0.08725521239472234, "rougeL_recall_stderr": 0.0030082346793116844, "rougeLsum_fmeasure": 0.0403293623763229, "rougeLsum_fmeasure_stderr": 0.0018133499923210787, "rougeLsum_precision": 0.04637512898059172, "rougeLsum_precision_stderr": 0.0025849567246808763, "rougeLsum_recall": 0.08219775751795474, "rougeLsum_recall_stderr": 0.0028538866420825446}, "pick_correct_choice_index": {"acc": 0.5038084874863983, "acc_norm": 0.5038084874863983, "acc_norm_stderr": 0.0116654857447468, "acc_stderr": 0.0116654857447468}, "what_is_the_correct_ending": {"acc": 0.5212187159956474, "acc_norm": 0.5223068552774756, "acc_norm_stderr": 0.011654208652596474, "acc_stderr": 0.011655314732288858}}, "2": {"Correct the solution": {"bleu": 13.894511213158287, "bleu_stderr": 0.8739525580726594, "rouge1_fmeasure": 0.3674980198284435, "rouge1_fmeasure_stderr": 0.00787898395002465, "rouge1_precision": 0.3962235671288584, "rouge1_precision_stderr": 0.008329795251643627, "rouge1_recall": 0.44796823076786213, "rouge1_recall_stderr": 0.008022473299790518, "rouge2_fmeasure": 0.25734856308354354, "rouge2_fmeasure_stderr": 0.0076839950683234475, "rouge2_precision": 0.27084269853025533, "rouge2_precision_stderr": 0.008065996347205293, "rouge2_recall": 0.31137177426270085, "rouge2_recall_stderr": 0.008133141525352511, "rougeL_fmeasure": 0.3543621394489363, "rougeL_fmeasure_stderr": 0.007955653293849538, "rougeL_precision": 0.37925499641508387, "rougeL_precision_stderr": 0.00832851687783064, "rougeL_recall": 0.4342613524811934, "rougeL_recall_stderr": 0.008157597971122069, "rougeLsum_fmeasure": 0.3559552758288509, "rougeLsum_fmeasure_stderr": 0.007950933392077896, "rougeLsum_precision": 0.3822857138351711, "rougeLsum_precision_stderr": 0.008360452943863943, "rougeLsum_recall": 0.4342525578898354, "rougeLsum_recall_stderr": 0.008116059673105629}, "choose the most appropriate solution": {"acc": 0.5043525571273123, "acc_norm": 0.5043525571273123, "acc_norm_stderr": 0.011665382144642399, "acc_stderr": 0.011665382144642399}, "no prompt needed": {"bleu": 0.2608651316164953, "bleu_stderr": 0.03978730347320043, "rouge1_fmeasure": 0.04266745301669875, "rouge1_fmeasure_stderr": 0.002122467346772042, "rouge1_precision": 0.05429344326618384, "rouge1_precision_stderr": 0.0029969628817093107, "rouge1_recall": 0.05806614564935589, "rouge1_recall_stderr": 0.0027269030308790685, "rouge2_fmeasure": 0.006554418985992436, "rouge2_fmeasure_stderr": 0.0007815781854311512, "rouge2_precision": 0.008207881019302006, "rouge2_precision_stderr": 0.0010086514951802858, "rouge2_recall": 0.008521702795534656, "rouge2_recall_stderr": 0.0010434649664570375, "rougeL_fmeasure": 0.036366524875545106, "rougeL_fmeasure_stderr": 0.0018289351480190433, "rougeL_precision": 0.04597127256330522, "rougeL_precision_stderr": 0.0025493206390164915, "rougeL_recall": 0.051020708361635456, "rougeL_recall_stderr": 0.0024526062149060925, "rougeLsum_fmeasure": 0.03690636788662361, "rougeLsum_fmeasure_stderr": 0.0018560807675874356, "rougeLsum_precision": 0.04719764857087024, "rougeLsum_precision_stderr": 0.0026618730300778984, "rougeLsum_recall": 0.050823488012879496, "rougeLsum_recall_stderr": 0.0024311881894851393}, "pick_correct_choice_index": {"acc": 0.4956474428726877, "acc_norm": 0.4956474428726877, "acc_norm_stderr": 0.011665382144642383, "acc_stderr": 0.011665382144642383}, "what_is_the_correct_ending": {"acc": 0.5255712731229597, "acc_norm": 0.5163220892274211, "acc_norm_stderr": 0.011659606710151779, "acc_stderr": 0.011650557844573578}}, "3": {"Correct the solution": {"bleu": 16.302962969684817, "bleu_stderr": 1.0914160471683245, "rouge1_fmeasure": 0.4159209145067388, "rouge1_fmeasure_stderr": 0.008066180840731338, "rouge1_precision": 0.44754150572005014, "rouge1_precision_stderr": 0.008508724146964648, "rouge1_recall": 0.4928656980785378, "rouge1_recall_stderr": 0.007959264981992405, "rouge2_fmeasure": 0.30169097752148116, "rouge2_fmeasure_stderr": 0.008003118328318673, "rouge2_precision": 0.31950165407284764, "rouge2_precision_stderr": 0.008430696030852732, "rouge2_recall": 0.35405055947121816, "rouge2_recall_stderr": 0.008289900831830925, "rougeL_fmeasure": 0.4021318671912827, "rougeL_fmeasure_stderr": 0.0081642603534126, "rougeL_precision": 0.4296491063999405, "rougeL_precision_stderr": 0.008545775185136658, "rougeL_recall": 0.47866238354613455, "rougeL_recall_stderr": 0.008119911722901458, "rougeLsum_fmeasure": 0.4041172336659238, "rougeLsum_fmeasure_stderr": 0.008150961646219602, "rougeLsum_precision": 0.43342040994924064, "rougeLsum_precision_stderr": 0.00856185501876351, "rougeLsum_recall": 0.47874998363575016, "rougeLsum_recall_stderr": 0.008081456218781254}, "choose the most appropriate solution": {"acc": 0.5016322089227421, "acc_norm": 0.5016322089227421, "acc_norm_stderr": 0.011665762007194866, "acc_stderr": 0.011665762007194866}, "no prompt needed": {"bleu": 0.22144147011965754, "bleu_stderr": 0.05131138433756984, "rouge1_fmeasure": 0.04452655769234325, "rouge1_fmeasure_stderr": 0.0021712328467205486, "rouge1_precision": 0.058386033932004415, "rouge1_precision_stderr": 0.0030880102581303886, "rouge1_recall": 0.05486532333879447, "rouge1_recall_stderr": 0.002608469514368819, "rouge2_fmeasure": 0.006348389170194352, "rouge2_fmeasure_stderr": 0.0007281347015003358, "rouge2_precision": 0.008602699160749428, "rouge2_precision_stderr": 0.0009813451014566705, "rouge2_recall": 0.007308424504803039, "rouge2_recall_stderr": 0.0008927033877862982, "rougeL_fmeasure": 0.038296677712480076, "rougeL_fmeasure_stderr": 0.0018715868727211123, "rougeL_precision": 0.05007522678633194, "rougeL_precision_stderr": 0.0026478813192163213, "rougeL_recall": 0.048399277860299794, "rougeL_recall_stderr": 0.0023392317754922483, "rougeLsum_fmeasure": 0.038779230929206605, "rougeLsum_fmeasure_stderr": 0.001893632110275806, "rougeLsum_precision": 0.05143163493997383, "rougeLsum_precision_stderr": 0.0027770376467427965, "rougeLsum_recall": 0.04819611262496829, "rougeLsum_recall_stderr": 0.0023229320235610062}, "pick_correct_choice_index": {"acc": 0.5250272034820457, "acc_norm": 0.5250272034820457, "acc_norm_stderr": 0.011651200967623707, "acc_stderr": 0.011651200967623707}, "what_is_the_correct_ending": {"acc": 0.5206746463547334, "acc_norm": 0.5163220892274211, "acc_norm_stderr": 0.011659606710151779, "acc_stderr": 0.011655846995729703}}, "4": {"Correct the solution": {"bleu": 18.29568798498642, "bleu_stderr": 0.8400045952338919, "rouge1_fmeasure": 0.440913771806968, "rouge1_fmeasure_stderr": 0.008161084155097175, "rouge1_precision": 0.47003616790222097, "rouge1_precision_stderr": 0.008492394610500243, "rouge1_recall": 0.5070618235168789, "rouge1_recall_stderr": 0.008034196403817398, "rouge2_fmeasure": 0.32589784419427137, "rouge2_fmeasure_stderr": 0.008140627546699501, "rouge2_precision": 0.34267924080360035, "rouge2_precision_stderr": 0.00849291013938346, "rouge2_recall": 0.3721650196784438, "rouge2_recall_stderr": 0.008345501652871087, "rougeL_fmeasure": 0.42864556356106626, "rougeL_fmeasure_stderr": 0.00825295711841848, "rougeL_precision": 0.4545619116360723, "rougeL_precision_stderr": 0.008535490921376865, "rougeL_recall": 0.49441236285200274, "rougeL_recall_stderr": 0.008175372919559136, "rougeLsum_fmeasure": 0.430525903474684, "rougeLsum_fmeasure_stderr": 0.008241357230569303, "rougeLsum_precision": 0.4575870105061546, "rougeLsum_precision_stderr": 0.008542975114188618, "rougeLsum_recall": 0.4951955460109368, "rougeLsum_recall_stderr": 0.008149833461155942}, "choose the most appropriate solution": {"acc": 0.5048966267682263, "acc_norm": 0.5048966267682263, "acc_norm_stderr": 0.011665264730078137, "acc_stderr": 0.011665264730078137}, "no prompt needed": {"bleu": 0.18473186157561908, "bleu_stderr": 0.04072950696800683, "rouge1_fmeasure": 0.05159212402267852, "rouge1_fmeasure_stderr": 0.0023638676475464648, "rouge1_precision": 0.06712446822614468, "rouge1_precision_stderr": 0.0033160597701479893, "rouge1_recall": 0.06019191056988439, "rouge1_recall_stderr": 0.002736892229053133, "rouge2_fmeasure": 0.0074306129720465705, "rouge2_fmeasure_stderr": 0.0007606984807758116, "rouge2_precision": 0.00964919360937356, "rouge2_precision_stderr": 0.0010051600074264555, "rouge2_recall": 0.008577476981962201, "rouge2_recall_stderr": 0.0009456245783267479, "rougeL_fmeasure": 0.045035878449402864, "rougeL_fmeasure_stderr": 0.002091652415092048, "rougeL_precision": 0.05818637904982665, "rougeL_precision_stderr": 0.0029044534046547958, "rougeL_recall": 0.05347769921709429, "rougeL_recall_stderr": 0.0024762222522701598, "rougeLsum_fmeasure": 0.04570769475572357, "rougeLsum_fmeasure_stderr": 0.0021186626160801304, "rougeLsum_precision": 0.059446564318682005, "rougeLsum_precision_stderr": 0.0029928762915145727, "rougeLsum_recall": 0.0537919766565263, "rougeLsum_recall_stderr": 0.0024838459656666596}, "pick_correct_choice_index": {"acc": 0.5239390642002176, "acc_norm": 0.5239390642002176, "acc_norm_stderr": 0.01165244562107926, "acc_stderr": 0.01165244562107926}, "what_is_the_correct_ending": {"acc": 0.5195865070729053, "acc_norm": 0.514145810663765, "acc_norm_stderr": 0.011661154475524835, "acc_stderr": 0.01165686997928846}}, "5": {"Correct the solution": {"bleu": 19.563665938000955, "bleu_stderr": 0.830837212255332, "rouge1_fmeasure": 0.45358632651135367, "rouge1_fmeasure_stderr": 0.008079574036676742, "rouge1_precision": 0.4850213774986562, "rouge1_precision_stderr": 0.008412810347685195, "rouge1_recall": 0.5175895233206349, "rouge1_recall_stderr": 0.007925276186417592, "rouge2_fmeasure": 0.33520179328257893, "rouge2_fmeasure_stderr": 0.008136267592204509, "rouge2_precision": 0.35233139121336177, "rouge2_precision_stderr": 0.008496659674238034, "rouge2_recall": 0.37841523275236855, "rouge2_recall_stderr": 0.008335884723129022, "rougeL_fmeasure": 0.44099249707631255, "rougeL_fmeasure_stderr": 0.00818874543924558, "rougeL_precision": 0.46894629707993607, "rougeL_precision_stderr": 0.008460443723532397, "rougeL_recall": 0.5041604671316591, "rougeL_recall_stderr": 0.008082489163576902, "rougeLsum_fmeasure": 0.442736079453689, "rougeLsum_fmeasure_stderr": 0.008170530134058251, "rougeLsum_precision": 0.4720370238207721, "rougeLsum_precision_stderr": 0.008475086337406505, "rougeLsum_recall": 0.5048483591695989, "rougeLsum_recall_stderr": 0.008038036370329855}, "choose the most appropriate solution": {"acc": 0.514145810663765, "acc_norm": 0.514145810663765, "acc_norm_stderr": 0.01166115447552484, "acc_stderr": 0.01166115447552484}, "no prompt needed": {"bleu": 0.3674534532595343, "bleu_stderr": 0.044535440751908385, "rouge1_fmeasure": 0.05237001461800124, "rouge1_fmeasure_stderr": 0.002390063573522162, "rouge1_precision": 0.06632940430625783, "rouge1_precision_stderr": 0.003221290438735765, "rouge1_recall": 0.06301059430183462, "rouge1_recall_stderr": 0.0028293221861692515, "rouge2_fmeasure": 0.008657019208894664, "rouge2_fmeasure_stderr": 0.0008613172115835112, "rouge2_precision": 0.010990734326689173, "rouge2_precision_stderr": 0.0011480661925135293, "rouge2_recall": 0.010346369422141026, "rouge2_recall_stderr": 0.0010512298188535155, "rougeL_fmeasure": 0.045594480368473495, "rougeL_fmeasure_stderr": 0.0020873498805373575, "rougeL_precision": 0.05733867044052891, "rougeL_precision_stderr": 0.002753785198676713, "rougeL_recall": 0.056005566309979465, "rougeL_recall_stderr": 0.0025635471231317537, "rougeLsum_fmeasure": 0.046277441891386925, "rougeLsum_fmeasure_stderr": 0.0021092213962826474, "rougeLsum_precision": 0.05908856304665778, "rougeLsum_precision_stderr": 0.0029043642978511183, "rougeLsum_recall": 0.05634193274869875, "rougeLsum_recall_stderr": 0.0025654170882293886}, "pick_correct_choice_index": {"acc": 0.5076169749727966, "acc_norm": 0.5076169749727966, "acc_norm_stderr": 0.011664470424044976, "acc_stderr": 0.011664470424044976}, "what_is_the_correct_ending": {"acc": 0.5125136017410229, "acc_norm": 0.5081610446137106, "acc_norm_stderr": 0.011664270112244223, "acc_stderr": 0.011662170084916892}}}, "sciq": {"0": {"Direct Question": {"acc": 0.663, "acc_norm": 0.567, "acc_norm_stderr": 0.01567663091218133, "acc_stderr": 0.014955087918653595}, "Direct Question (Closed Book)": {"acc": 0.365, "acc_norm": 0.36, "acc_norm_stderr": 0.015186527932040122, "acc_stderr": 0.015231776226264914}, "Multiple Choice": {"acc": 0.482, "acc_norm": 0.438, "acc_norm_stderr": 0.01569721001969469, "acc_stderr": 0.015809045699406728}, "Multiple Choice (Closed Book)": {"acc": 0.372, "acc_norm": 0.347, "acc_norm_stderr": 0.015060472031706618, "acc_stderr": 0.015292149942040577}, "Multiple Choice Question First": {"acc": 0.516, "acc_norm": 0.434, "acc_norm_stderr": 0.015680876566375058, "acc_stderr": 0.015811198373114878}}, "1": {"Direct Question": {"acc": 0.715, "acc_norm": 0.648, "acc_norm_stderr": 0.015110404505648661, "acc_stderr": 0.014282120955200485}, "Direct Question (Closed Book)": {"acc": 0.393, "acc_norm": 0.388, "acc_norm_stderr": 0.015417317979911076, "acc_stderr": 0.015452824654081496}, "Multiple Choice": {"acc": 0.335, "acc_norm": 0.355, "acc_norm_stderr": 0.015139491543780532, "acc_stderr": 0.014933117490932573}, "Multiple Choice (Closed Book)": {"acc": 0.32, "acc_norm": 0.329, "acc_norm_stderr": 0.014865395385928362, "acc_stderr": 0.014758652303574874}, "Multiple Choice Question First": {"acc": 0.395, "acc_norm": 0.406, "acc_norm_stderr": 0.015537226438634602, "acc_stderr": 0.015466551464829342}}, "2": {"Direct Question": {"acc": 0.71, "acc_norm": 0.664, "acc_norm_stderr": 0.014944140233795023, "acc_stderr": 0.01435639599990569}, "Direct Question (Closed Book)": {"acc": 0.386, "acc_norm": 0.387, "acc_norm_stderr": 0.015410011955493932, "acc_stderr": 0.015402637476784385}, "Multiple Choice": {"acc": 0.28, "acc_norm": 0.282, "acc_norm_stderr": 0.014236526215291343, "acc_stderr": 0.014205696104091512}, "Multiple Choice (Closed Book)": {"acc": 0.276, "acc_norm": 0.291, "acc_norm_stderr": 0.014370995982377946, "acc_stderr": 0.014142984975740668}, "Multiple Choice Question First": {"acc": 0.323, "acc_norm": 0.324, "acc_norm_stderr": 0.014806864733738859, "acc_stderr": 0.014794927843348632}}, "3": {"Direct Question": {"acc": 0.722, "acc_norm": 0.682, "acc_norm_stderr": 0.014734079309311901, "acc_stderr": 0.014174516461485265}, "Direct Question (Closed Book)": {"acc": 0.383, "acc_norm": 0.379, "acc_norm_stderr": 0.01534909100222535, "acc_stderr": 0.01538010232565271}, "Multiple Choice": {"acc": 0.28, "acc_norm": 0.293, "acc_norm_stderr": 0.014399942998441275, "acc_stderr": 0.014205696104091512}, "Multiple Choice (Closed Book)": {"acc": 0.3, "acc_norm": 0.308, "acc_norm_stderr": 0.01460648312734276, "acc_stderr": 0.014498627873361425}, "Multiple Choice Question First": {"acc": 0.319, "acc_norm": 0.329, "acc_norm_stderr": 0.014865395385928357, "acc_stderr": 0.014746404865473494}}, "4": {"Direct Question": {"acc": 0.724, "acc_norm": 0.7, "acc_norm_stderr": 0.01449862787336143, "acc_stderr": 0.014142984975740668}, "Direct Question (Closed Book)": {"acc": 0.393, "acc_norm": 0.388, "acc_norm_stderr": 0.015417317979911076, "acc_stderr": 0.015452824654081496}, "Multiple Choice": {"acc": 0.308, "acc_norm": 0.322, "acc_norm_stderr": 0.014782913600996662, "acc_stderr": 0.014606483127342761}, "Multiple Choice (Closed Book)": {"acc": 0.306, "acc_norm": 0.331, "acc_norm_stderr": 0.01488827258820393, "acc_stderr": 0.014580006055436965}, "Multiple Choice Question First": {"acc": 0.322, "acc_norm": 0.327, "acc_norm_stderr": 0.014842213153411247, "acc_stderr": 0.014782913600996664}}, "5": {"Direct Question": {"acc": 0.728, "acc_norm": 0.695, "acc_norm_stderr": 0.014566646394664382, "acc_stderr": 0.014078856992462621}, "Direct Question (Closed Book)": {"acc": 0.384, "acc_norm": 0.388, "acc_norm_stderr": 0.015417317979911077, "acc_stderr": 0.015387682761897068}, "Multiple Choice": {"acc": 0.289, "acc_norm": 0.292, "acc_norm_stderr": 0.01438551156347735, "acc_stderr": 0.014341711358296177}, "Multiple Choice (Closed Book)": {"acc": 0.298, "acc_norm": 0.308, "acc_norm_stderr": 0.014606483127342763, "acc_stderr": 0.014470846741134722}, "Multiple Choice Question First": {"acc": 0.313, "acc_norm": 0.309, "acc_norm_stderr": 0.014619600977206482, "acc_stderr": 0.014671272822977881}}}, "story_cloze_2016": {"0": {"Answer Given options": {"acc": 0.48583645109567075, "acc_norm": 0.48850881881346875, "acc_norm_stderr": 0.011559378273599123, "acc_stderr": 0.011557792331301673}, "Choose Story Ending": {"acc": 0.5066809192944949, "acc_norm": 0.5259219668626403, "acc_norm_stderr": 0.011546883081384901, "acc_stderr": 0.011561400034509398}, "Novel Correct Ending": {"acc": 0.47728487439871725, "acc_norm": 0.48476750400855156, "acc_norm_stderr": 0.011557065368348286, "acc_stderr": 0.011550494192008947}, "Story Continuation and Options": {"acc": 0.49812934259754144, "acc_norm": 0.5189738107963656, "acc_norm_stderr": 0.0115541041740197, "acc_stderr": 0.011562351329083266}}, "1": {"Answer Given options": {"acc": 0.47835382148583644, "acc_norm": 0.4890432923570283, "acc_norm_stderr": 0.011559655791130734, "acc_stderr": 0.011551591851683333}, "Choose Story Ending": {"acc": 0.47835382148583644, "acc_norm": 0.49438802779262425, "acc_norm_stderr": 0.011561703928784335, "acc_stderr": 0.011551591851683333}, "Novel Correct Ending": {"acc": 0.47247461250668094, "acc_norm": 0.48476750400855156, "acc_norm_stderr": 0.011557065368348288, "acc_stderr": 0.011544898473864581}, "Story Continuation and Options": {"acc": 0.4794227685729556, "acc_norm": 0.48850881881346875, "acc_norm_stderr": 0.011559378273599118, "acc_stderr": 0.011552636515221862}}, "2": {"Answer Given options": {"acc": 0.4767504008551577, "acc_norm": 0.47728487439871725, "acc_norm_stderr": 0.011550494192008943, "acc_stderr": 0.01154992548392746}, "Choose Story Ending": {"acc": 0.4794227685729556, "acc_norm": 0.4906467129877071, "acc_norm_stderr": 0.011560409019420362, "acc_stderr": 0.011552636515221862}, "Novel Correct Ending": {"acc": 0.4719401389631213, "acc_norm": 0.47728487439871725, "acc_norm_stderr": 0.011550494192008943, "acc_stderr": 0.011544210396951667}, "Story Continuation and Options": {"acc": 0.4740780331373597, "acc_norm": 0.4831640833778728, "acc_norm_stderr": 0.011555875693960773, "acc_stderr": 0.011546883081384903}}, "3": {"Answer Given options": {"acc": 0.4681988241582042, "acc_norm": 0.4836985569214324, "acc_norm_stderr": 0.011556285484521566, "acc_stderr": 0.01153902203511123}, "Choose Story Ending": {"acc": 0.4751469802244789, "acc_norm": 0.4735435595938001, "acc_norm_stderr": 0.011546234813777404, "acc_stderr": 0.01154813982307477}, "Novel Correct Ending": {"acc": 0.4692677712453234, "acc_norm": 0.47728487439871725, "acc_norm_stderr": 0.011550494192008941, "acc_stderr": 0.011540570846495544}, "Story Continuation and Options": {"acc": 0.467129877071085, "acc_norm": 0.4767504008551577, "acc_norm_stderr": 0.011549925483927456, "acc_stderr": 0.0115374200542103}}, "4": {"Answer Given options": {"acc": 0.467129877071085, "acc_norm": 0.4756814537680385, "acc_norm_stderr": 0.01154874830148732, "acc_stderr": 0.011537420054210303}, "Choose Story Ending": {"acc": 0.467129877071085, "acc_norm": 0.4692677712453234, "acc_norm_stderr": 0.011540570846495542, "acc_stderr": 0.011537420054210303}, "Novel Correct Ending": {"acc": 0.4660609299839658, "acc_norm": 0.4708711918760021, "acc_norm_stderr": 0.011542794417345717, "acc_stderr": 0.011535764881641411}, "Story Continuation and Options": {"acc": 0.46392303580972744, "acc_norm": 0.47033671833244256, "acc_norm_stderr": 0.011542066509767012, "acc_stderr": 0.01153229486915312}}, "5": {"Answer Given options": {"acc": 0.46392303580972744, "acc_norm": 0.47247461250668094, "acc_norm_stderr": 0.011544898473864583, "acc_stderr": 0.01153229486915312}, "Choose Story Ending": {"acc": 0.45911277391769106, "acc_norm": 0.46873329770176375, "acc_norm_stderr": 0.011539803085637734, "acc_stderr": 0.01152370806018208}, "Novel Correct Ending": {"acc": 0.4580438268305719, "acc_norm": 0.4649919828968466, "acc_norm_stderr": 0.011534056494505859, "acc_stderr": 0.011521653168224729}, "Story Continuation and Options": {"acc": 0.4537680384820951, "acc_norm": 0.4633885622661678, "acc_norm_stderr": 0.011531394084549623, "acc_stderr": 0.011512899199863038}}}, "superglue_rte": {"0": {"GPT-3 style": {"acc": 0.5342960288808665, "acc_norm": 0.4729241877256318, "acc_norm_stderr": 0.030052303463143706, "acc_stderr": 0.03002557981936642}, "MNLI crowdsource": {"acc": 0.5270758122743683, "acc_norm": 0.5270758122743683, "acc_norm_stderr": 0.030052303463143706, "acc_stderr": 0.030052303463143706}, "does it follow that": {"acc": 0.5054151624548736, "acc_norm": 0.5270758122743683, "acc_norm_stderr": 0.030052303463143706, "acc_stderr": 0.030094698123239966}, "guaranteed true": {"acc": 0.5270758122743683, "acc_norm": 0.5270758122743683, "acc_norm_stderr": 0.030052303463143706, "acc_stderr": 0.030052303463143706}, "should assume": {"acc": 0.5270758122743683, "acc_norm": 0.5270758122743683, "acc_norm_stderr": 0.030052303463143706, "acc_stderr": 0.030052303463143706}}, "1": {"GPT-3 style": {"acc": 0.4981949458483754, "acc_norm": 0.5018050541516246, "acc_norm_stderr": 0.030096267148976626, "acc_stderr": 0.030096267148976633}, "MNLI crowdsource": {"acc": 0.5306859205776173, "acc_norm": 0.5415162454873647, "acc_norm_stderr": 0.029992535385373314, "acc_stderr": 0.030039730592197812}, "does it follow that": {"acc": 0.49458483754512633, "acc_norm": 0.5090252707581228, "acc_norm_stderr": 0.030091559826331334, "acc_stderr": 0.030094698123239966}, "guaranteed true": {"acc": 0.48375451263537905, "acc_norm": 0.47653429602888087, "acc_norm_stderr": 0.03006330041190266, "acc_stderr": 0.030080573208738064}, "should assume": {"acc": 0.4981949458483754, "acc_norm": 0.5234657039711191, "acc_norm_stderr": 0.03006330041190266, "acc_stderr": 0.030096267148976633}}, "2": {"GPT-3 style": {"acc": 0.5234657039711191, "acc_norm": 0.5234657039711191, "acc_norm_stderr": 0.030063300411902652, "acc_stderr": 0.030063300411902652}, "MNLI crowdsource": {"acc": 0.5090252707581228, "acc_norm": 0.516245487364621, "acc_norm_stderr": 0.030080573208738064, "acc_stderr": 0.030091559826331334}, "does it follow that": {"acc": 0.5054151624548736, "acc_norm": 0.5054151624548736, "acc_norm_stderr": 0.030094698123239966, "acc_stderr": 0.030094698123239966}, "guaranteed true": {"acc": 0.5018050541516246, "acc_norm": 0.5090252707581228, "acc_norm_stderr": 0.030091559826331334, "acc_stderr": 0.030096267148976633}, "should assume": {"acc": 0.5126353790613718, "acc_norm": 0.5090252707581228, "acc_norm_stderr": 0.030091559826331334, "acc_stderr": 0.030086851767188564}}, "3": {"GPT-3 style": {"acc": 0.516245487364621, "acc_norm": 0.49097472924187724, "acc_norm_stderr": 0.030091559826331334, "acc_stderr": 0.030080573208738064}, "MNLI crowdsource": {"acc": 0.5234657039711191, "acc_norm": 0.51985559566787, "acc_norm_stderr": 0.030072723167317177, "acc_stderr": 0.03006330041190266}, "does it follow that": {"acc": 0.5126353790613718, "acc_norm": 0.516245487364621, "acc_norm_stderr": 0.030080573208738064, "acc_stderr": 0.030086851767188564}, "guaranteed true": {"acc": 0.516245487364621, "acc_norm": 0.5234657039711191, "acc_norm_stderr": 0.03006330041190266, "acc_stderr": 0.030080573208738064}, "should assume": {"acc": 0.5270758122743683, "acc_norm": 0.5234657039711191, "acc_norm_stderr": 0.03006330041190266, "acc_stderr": 0.030052303463143706}}, "4": {"GPT-3 style": {"acc": 0.5054151624548736, "acc_norm": 0.5090252707581228, "acc_norm_stderr": 0.030091559826331334, "acc_stderr": 0.030094698123239966}, "MNLI crowdsource": {"acc": 0.516245487364621, "acc_norm": 0.5306859205776173, "acc_norm_stderr": 0.030039730592197816, "acc_stderr": 0.030080573208738064}, "does it follow that": {"acc": 0.5018050541516246, "acc_norm": 0.5126353790613718, "acc_norm_stderr": 0.030086851767188564, "acc_stderr": 0.030096267148976626}, "guaranteed true": {"acc": 0.5126353790613718, "acc_norm": 0.516245487364621, "acc_norm_stderr": 0.030080573208738064, "acc_stderr": 0.030086851767188564}, "should assume": {"acc": 0.5342960288808665, "acc_norm": 0.5342960288808665, "acc_norm_stderr": 0.030025579819366426, "acc_stderr": 0.030025579819366426}}, "5": {"GPT-3 style": {"acc": 0.5018050541516246, "acc_norm": 0.5054151624548736, "acc_norm_stderr": 0.030094698123239966, "acc_stderr": 0.030096267148976633}, "MNLI crowdsource": {"acc": 0.516245487364621, "acc_norm": 0.5126353790613718, "acc_norm_stderr": 0.030086851767188564, "acc_stderr": 0.030080573208738064}, "does it follow that": {"acc": 0.4981949458483754, "acc_norm": 0.516245487364621, "acc_norm_stderr": 0.030080573208738064, "acc_stderr": 0.030096267148976633}, "guaranteed true": {"acc": 0.5126353790613718, "acc_norm": 0.51985559566787, "acc_norm_stderr": 0.030072723167317177, "acc_stderr": 0.030086851767188564}, "should assume": {"acc": 0.5126353790613718, "acc_norm": 0.5054151624548736, "acc_norm_stderr": 0.030094698123239966, "acc_stderr": 0.030086851767188564}}}, "winogrande": {"0": {"Replace": {"acc": 0.4996053670086819, "acc_norm": 0.49329123914759276, "acc_norm_stderr": 0.014051220692330346, "acc_stderr": 0.014052481306049512}, "True or False": {"acc": 0.494869771112865, "acc_norm": 0.47908445146014206, "acc_norm_stderr": 0.014040185494212952, "acc_stderr": 0.014051745961790516}, "does underscore refer to": {"acc": 0.494869771112865, "acc_norm": 0.4988161010260458, "acc_norm_stderr": 0.014052446290529024, "acc_stderr": 0.014051745961790516}, "stand for": {"acc": 0.4940805051302289, "acc_norm": 0.48697711128650356, "acc_norm_stderr": 0.014047718393997667, "acc_stderr": 0.014051500838485807}, "underscore refer to": {"acc": 0.4940805051302289, "acc_norm": 0.4980268350434096, "acc_norm_stderr": 0.014052376259225636, "acc_stderr": 0.014051500838485807}}, "1": {"Replace": {"acc": 0.5035516969218626, "acc_norm": 0.5019731649565904, "acc_norm_stderr": 0.014052376259225632, "acc_stderr": 0.014052131146915864}, "True or False": {"acc": 0.5011838989739542, "acc_norm": 0.505130228887135, "acc_norm_stderr": 0.014051745961790513, "acc_stderr": 0.014052446290529012}, "does underscore refer to": {"acc": 0.5209155485398579, "acc_norm": 0.505130228887135, "acc_norm_stderr": 0.014051745961790513, "acc_stderr": 0.014040185494212947}, "stand for": {"acc": 0.5059194948697711, "acc_norm": 0.4988161010260458, "acc_norm_stderr": 0.014052446290529024, "acc_stderr": 0.014051500838485807}, "underscore refer to": {"acc": 0.4988161010260458, "acc_norm": 0.5059194948697711, "acc_norm_stderr": 0.01405150083848581, "acc_stderr": 0.014052446290529015}}, "2": {"Replace": {"acc": 0.4996053670086819, "acc_norm": 0.4940805051302289, "acc_norm_stderr": 0.01405150083848581, "acc_stderr": 0.014052481306049516}, "True or False": {"acc": 0.5098658247829518, "acc_norm": 0.500394632991318, "acc_norm_stderr": 0.014052481306049516, "acc_stderr": 0.014049749833367596}, "does underscore refer to": {"acc": 0.49329123914759276, "acc_norm": 0.5074980268350434, "acc_norm_stderr": 0.01405090552122858, "acc_stderr": 0.014051220692330349}, "stand for": {"acc": 0.5035516969218626, "acc_norm": 0.494869771112865, "acc_norm_stderr": 0.01405174596179052, "acc_stderr": 0.014052131146915853}, "underscore refer to": {"acc": 0.5130228887134964, "acc_norm": 0.5153906866614049, "acc_norm_stderr": 0.014045826789783658, "acc_stderr": 0.01404771839399767}}, "3": {"Replace": {"acc": 0.4956590370955012, "acc_norm": 0.5027624309392266, "acc_norm_stderr": 0.014052271211616436, "acc_stderr": 0.014051956064076892}, "True or False": {"acc": 0.5059194948697711, "acc_norm": 0.5114443567482242, "acc_norm_stderr": 0.014048804199859325, "acc_stderr": 0.014051500838485807}, "does underscore refer to": {"acc": 0.489344909234412, "acc_norm": 0.5074980268350434, "acc_norm_stderr": 0.01405090552122858, "acc_stderr": 0.0140492945362904}, "stand for": {"acc": 0.5114443567482242, "acc_norm": 0.5019731649565904, "acc_norm_stderr": 0.014052376259225636, "acc_stderr": 0.014048804199859325}, "underscore refer to": {"acc": 0.5035516969218626, "acc_norm": 0.5043409629044988, "acc_norm_stderr": 0.014051956064076906, "acc_stderr": 0.014052131146915867}}, "4": {"Replace": {"acc": 0.4925019731649566, "acc_norm": 0.500394632991318, "acc_norm_stderr": 0.01405248130604952, "acc_stderr": 0.014050905521228573}, "True or False": {"acc": 0.5201262825572218, "acc_norm": 0.5288082083662194, "acc_norm_stderr": 0.014029141615909617, "acc_stderr": 0.01404109666434433}, "does underscore refer to": {"acc": 0.48303078137332284, "acc_norm": 0.5082872928176796, "acc_norm_stderr": 0.014050555322824189, "acc_stderr": 0.014044390401612976}, "stand for": {"acc": 0.5059194948697711, "acc_norm": 0.494869771112865, "acc_norm_stderr": 0.014051745961790523, "acc_stderr": 0.014051500838485807}, "underscore refer to": {"acc": 0.516179952644041, "acc_norm": 0.5185477505919495, "acc_norm_stderr": 0.014042813708888378, "acc_stderr": 0.014045126130978594}}, "5": {"Replace": {"acc": 0.4980268350434096, "acc_norm": 0.49171270718232046, "acc_norm_stderr": 0.014050555322824194, "acc_stderr": 0.014052376259225636}, "True or False": {"acc": 0.5185477505919495, "acc_norm": 0.5138121546961326, "acc_norm_stderr": 0.014047122916440415, "acc_stderr": 0.014042813708888378}, "does underscore refer to": {"acc": 0.5043409629044988, "acc_norm": 0.5090765588003157, "acc_norm_stderr": 0.014050170094497704, "acc_stderr": 0.014051956064076892}, "stand for": {"acc": 0.5043409629044988, "acc_norm": 0.5074980268350434, "acc_norm_stderr": 0.014050905521228573, "acc_stderr": 0.0140519560640769}, "underscore refer to": {"acc": 0.5146014206787688, "acc_norm": 0.5146014206787688, "acc_norm_stderr": 0.01404649238327584, "acc_stderr": 0.014046492383275837}}}} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b8013f82b4d1ee1732e3febdd3c77aa4b8c2f260 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.2882702237124178, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.03507359582313697 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.07300904609224831, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0029525045593291944 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.23319598837092428, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004717928243407737 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.09304445819797845, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0021071281123058827 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.031781240194588535, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.001647655179664631 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.11446696473056167, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0030078380901265153 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.04357651166126725, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0012628931036486493 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.07148927214916825, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0028994443219541085 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.22962123752434357, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004651057204662988 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.09113938986614295, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.002025825990715642 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.06999428575198861, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0029010892622887635 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.22168579525487217, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0043756801267272015 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08853812013819903, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019810527750856927 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.json new file mode 100644 index 0000000000000000000000000000000000000000..58ec478baecd63e6b297ff03efd7f0f89fef4d61 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.22276279918601394, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.018133211573574757 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.06067991294954199, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.002071772799498889 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.20293836364892254, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004213962706134935 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.0827185269757938, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001999403821307096 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.02515093170386624, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0012657693333304634 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.0927272131857222, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00270796998310677 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.03533725838532431, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011679547214428377 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.05782243575115753, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0019660354949123677 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.19744065879364792, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004113784957628094 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.07920096600543666, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018627056924898366 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.05802381954191155, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0019924692015719286 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.19618466537860657, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0040253079050866485 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.07922447831134258, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018815454632281374 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2cb7fc30dba135e209a96b6487380bc0728dd3c8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.22816452014689217, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.021011094086360756 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.0643252880050605, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001873211164048415 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.21568616317061653, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004082948724364347 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.0888316472488794, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002008077222359181 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.02624513151161159, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.001151855832984562 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.09761833567947041, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0026995300080965585 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.03698279772417711, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011212628433211664 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.0606248912817486, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001701220213613193 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.20937007549926187, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.003993668186702462 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.08454134203955807, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018430886624515794 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.06105372863643947, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001737959743755711 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.20931532337002748, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003964000228350047 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08484366265533932, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018647506310172767 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.json new file mode 100644 index 0000000000000000000000000000000000000000..6f19c73d35364d31ac1c6f519f20a79882f948a9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.21668033919612437, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.020179750003043416 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.06599850329511878, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0020196888536449255 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.2189549242330715, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.00402494120221226 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.09037007800347752, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0021075393335480913 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.026861010489235518, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0010411924138277121 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.09848799682900536, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002619448977397938 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.037900350601950995, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011762008290810827 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.0616752271189791, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0017718026569788809 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.2115279407271533, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0038925777592653194 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.0854553995007257, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018898385438172103 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.0623910245818171, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0018474876713692014 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.2116287101661098, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0038714328117695138 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08596309183671783, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001927157623088893 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.json new file mode 100644 index 0000000000000000000000000000000000000000..1846dbb2b20ef3699fbfb79b0984699b99521a20 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.22324841354029434, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.012884365211201858 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.06502648081363527, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0019568795906677195 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.22314967057311585, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004060178019176997 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.08984024388721441, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002049686525188311 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.027172974346249407, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0010775269042031367 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.10278841213516382, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0026896302440292856 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.038427620423283494, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011342309564967815 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.06051581313878435, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001686918901782139 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.21546541192297525, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0039050941983854084 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.08475169911603465, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018041950412597118 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.06149322300624985, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0017642592919849167 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.21601509705224456, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003902368298687872 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08562046048144208, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018622202648950923 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.json new file mode 100644 index 0000000000000000000000000000000000000000..fa9c1bcc8ac5fb31e5f427443a92e3d5d6403a48 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_PALM_prompt_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.21464230162703427, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.01244691129274461 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.06952443270444716, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0022809171687925307 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.23024280021949023, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.00409858662928981 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.09216278427137457, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002102114353680242 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.027750881647517683, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011006386822245205 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.10600678669436031, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002763944580059492 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.03892365918376217, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011826072971332408 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.06485734355722127, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.002020231716412655 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.22257612852322436, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.003940687874091731 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.08717550041439592, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018759391818764337 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.06592417348285784, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0021091163919465493 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.22298794088967588, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003928367080650771 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08796230830100418, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019209922626217265 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2fdf67400e784bf893eb2457f1ff701066d9ed66 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_precision": 0.007871384048100007, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0008027273679290646 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_recall": 0.025894899249411275, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001510927848658749 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_fmeasure": 0.007735199321992511, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0004929168751900662 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_precision": 0.00018612440324107684, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00010813827959713304 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_recall": 0.00113072926486338, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0002538916851940024 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_fmeasure": 0.00024213283343663074, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00010293363022896083 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_precision": 0.007831916501187445, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0007926431382581877 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_recall": 0.02584550434779307, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0015047949229976157 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_fmeasure": 0.007693913912486717, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.00047606068305271974 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_precision": 0.006437589464226677, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0007714572173800608 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_recall": 0.018623470093568916, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0011493529601984355 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_fmeasure": 0.0054174592644268636, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0003711886426354486 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "bleu": 0.002413992658676713, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.00013676206143739094 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.json new file mode 100644 index 0000000000000000000000000000000000000000..1c57393667d0b23ec08365e4aa5af80f5d02b992 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_precision": 0.17162164691878115, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.002541153433910131 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_recall": 0.1570833115237782, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0023628047156862182 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_fmeasure": 0.14455688747960732, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0018065881001650948 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_precision": 0.017746162480695066, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011795108909179546 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_recall": 0.01659075032220689, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0010082231571640825 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_fmeasure": 0.014443686344970957, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0008315132954917715 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_precision": 0.14445360743779065, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0021746805211461384 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_recall": 0.13201397388417854, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0019716702901784876 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_fmeasure": 0.12055575191673172, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0014352825043199523 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_precision": 0.1529221545748428, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.002295493453246678 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_recall": 0.13941491139639123, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0020642758193953298 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_fmeasure": 0.12789813539780287, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0015529949122606935 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "bleu": 0.7346171507567223, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.13707913782304798 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.json new file mode 100644 index 0000000000000000000000000000000000000000..30de5fbb404329f6314fc3bf091d9fe5a899dfac --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_precision": 0.20663907836610496, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0033829599247524127 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_recall": 0.2479349663972334, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0044131481989255214 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_fmeasure": 0.18740801320012218, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0026759273447015666 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_precision": 0.044514823553754815, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0020773970237284085 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_recall": 0.06392575894949451, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002576650238805862 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_fmeasure": 0.04163806201461763, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001744964461999939 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_precision": 0.17383935881323387, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0029141796169836406 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_recall": 0.21185220120183285, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.00391960722018384 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_fmeasure": 0.15705135749100313, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0022404431287739728 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_precision": 0.18333789821164648, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0030290826006994917 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_recall": 0.2176069260272544, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003804234575122432 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_fmeasure": 0.16490115686406231, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0023344806701187824 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "bleu": 0.8566894201349882, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.08624072055130635 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.json new file mode 100644 index 0000000000000000000000000000000000000000..862692cd16b165241508b0e3607686551cde92fc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_precision": 0.23700393129285693, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.003998832100987239 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_recall": 0.26444744204782306, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004491563559631609 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_fmeasure": 0.20662215475852175, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0029093584177742257 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_precision": 0.0618205621459243, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0025531310938124367 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_recall": 0.07796583472925955, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0027407400714859207 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_fmeasure": 0.05445999669995589, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00197546840586398 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_precision": 0.1993414050245294, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0034880359309727806 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_recall": 0.2262831386525155, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004000931690515669 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_fmeasure": 0.1731669889234156, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0024412054531090356 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_precision": 0.21007336129721205, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.003603119181953105 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_recall": 0.23246013837952773, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003889246478806612 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_fmeasure": 0.18190324751556092, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002538737343530949 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "bleu": 1.0569147515296082, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.0894097345506189 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.json new file mode 100644 index 0000000000000000000000000000000000000000..dfb288f9baf1f937cb7140766036e64d9c1f0cae --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_precision": 0.24343442215612912, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.004290336159466549 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_recall": 0.2937677188486643, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.00476022029269311 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_fmeasure": 0.21768757196984853, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0030964308114536637 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_precision": 0.07382521753054258, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.002822725067559204 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_recall": 0.09629906393146742, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0030384383273633826 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_fmeasure": 0.06572301772314433, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0022002247062358235 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_precision": 0.2052733017686618, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0037268495898633647 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_recall": 0.252355975266905, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004227144384953933 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_fmeasure": 0.18281448217767138, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.002566640286607954 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_precision": 0.21562448887139193, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.003855934210118673 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_recall": 0.2578416353472927, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004098132845796672 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_fmeasure": 0.1915680837153, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0026965258074827755 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "bleu": 1.1744154279568062, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.10900900384288126 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b16df8bd4449a75b891bf518ca1986a602ebb0dc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_explicit-graph-description2_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_precision": 0.25749968628071634, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.004557872484881917 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_recall": 0.2952708397989195, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004728252484609096 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge1_fmeasure": 0.22576005910143196, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0032791573262992177 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_precision": 0.08269685100109506, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.003027333731786083 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_recall": 0.10110655349024573, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0031054606964476387 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rouge2_fmeasure": 0.07189912423622183, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0023282015023082664 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_precision": 0.21853685082560628, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0039871118588556366 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_recall": 0.25492080968482705, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.00420711638229053 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeL_fmeasure": 0.19074926578003074, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0027348190562132136 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_precision": 0.22916016865925895, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.00411577700341045 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_recall": 0.260297323377531, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.00409556008633347 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "rougeLsum_fmeasure": 0.19945385414430314, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0028579749339794932 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "explicit-graph-description2", + "bleu": 1.2744890026821296, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.09553029750807113 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d12822cfb73f22857ac794c959970442e52b1f8d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "bleu": 0.138569878297038, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.031551101184468404 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_precision": 0.03724302186557898, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0022152532951271718 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_recall": 0.22526135818945897, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.003344792850841178 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_fmeasure": 0.04792939313815056, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0009615050147245499 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_precision": 0.005393881463397369, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0003489838735994459 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_recall": 0.04305719338313865, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0019680551642618054 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_fmeasure": 0.008626127762314056, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0004981474293610044 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_precision": 0.03600954286370912, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0021750052445456717 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_recall": 0.22113346749553864, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0032963184671457187 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_fmeasure": 0.046408969912627086, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008900420023077054 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_precision": 0.0326382629292867, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.002191301787071691 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_recall": 0.18954584534668284, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0028756146093179826 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_fmeasure": 0.040241405686779766, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0008508436852286362 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.json new file mode 100644 index 0000000000000000000000000000000000000000..5a8caa0dc7423e3874db9d264e52e7475ad7e5ef --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "bleu": 0.7190193263389013, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.13634910774619252 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_precision": 0.1677909378471085, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0025279575952143075 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_recall": 0.1557256533318373, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0024294408093670523 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_fmeasure": 0.14139180219702063, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001814619491045361 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_precision": 0.016973478974085843, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011314265139906986 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_recall": 0.01638165201377114, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009960548800777898 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_fmeasure": 0.01386135386977246, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0007977730891733734 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_precision": 0.14118769936973508, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0021616686394079765 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_recall": 0.1311490160490549, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0020570345011630387 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_fmeasure": 0.11787997771951876, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0014405006728974714 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_precision": 0.14939682437853644, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0022883954744429844 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_recall": 0.1379569195179203, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002111952939893884 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_fmeasure": 0.12499033357696115, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0015650259493247992 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.json new file mode 100644 index 0000000000000000000000000000000000000000..85a804b3467634f4f3fcb4b381d9d273751a0ced --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "bleu": 0.654858159962283, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.05090283227203148 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_precision": 0.18587109175652072, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0032528462646382837 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_recall": 0.25339458245702867, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004577585923235268 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_fmeasure": 0.1718578502584956, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.00246372252095823 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_precision": 0.038492631218654094, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0018039997248216703 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_recall": 0.0713821989527362, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0027007946811370516 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_fmeasure": 0.03832506645342158, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0014998680640168213 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_precision": 0.1565380855202379, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.002747157296710683 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_recall": 0.22294560743499395, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004308467347707439 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_fmeasure": 0.14549486942641893, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0020319539502286887 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_precision": 0.16369817034532635, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0028970310154362226 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_recall": 0.22068224654084853, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0039045572017400235 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_fmeasure": 0.14994420152341253, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002110161728007287 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ad66b1c8734487224e80a9d0600a5e65e9afbb58 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "bleu": 0.8662810235466556, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.09404503161396437 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_precision": 0.21630507113127517, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0037635681346209204 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_recall": 0.29385220234946363, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004939943721033626 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_fmeasure": 0.19757579221778704, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002740581812349554 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_precision": 0.05540012459456432, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.002226210322926932 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_recall": 0.09790333465592813, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003133062562474596 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_fmeasure": 0.05353042851216683, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0018154897675158883 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_precision": 0.1839111737113415, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0032708663113493845 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_recall": 0.2610670692827167, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004730435390915318 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_fmeasure": 0.1686567646585531, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.00233205958797479 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_precision": 0.19108993104157018, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.00343247374642446 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_recall": 0.25510045795061914, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004229656468015747 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_fmeasure": 0.17281728476431374, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002423817934865248 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.json new file mode 100644 index 0000000000000000000000000000000000000000..24fbb41907784f071de48625aa989045a6223e89 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "bleu": 0.8327592530541046, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.08252044356912364 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_precision": 0.22591578566077025, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0040744177303127975 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_recall": 0.3271371159734268, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004954912621561014 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_fmeasure": 0.20994644193209497, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002856480485934521 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_precision": 0.06610289029069367, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0024587911594638476 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_recall": 0.11815894609420728, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003294870975442443 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_fmeasure": 0.06406636511396212, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001978008075438107 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_precision": 0.19179087245553803, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0034654596797486763 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_recall": 0.29163613239456493, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004772453186076372 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_fmeasure": 0.1795827877529302, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0024101179259044926 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_precision": 0.1981303722652317, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0036291877325131637 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_recall": 0.28411489421280556, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004268909617622095 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_fmeasure": 0.18295052341283213, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0025224970561372752 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.json new file mode 100644 index 0000000000000000000000000000000000000000..ed28c070c61c8a10b1ea06cec3b585537c4d5926 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_implicit-graph-description_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "bleu": 0.9864896153661107, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.1114488450591458 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_precision": 0.24687269679032836, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.004501369815547214 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_recall": 0.3404419977444704, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.005025782336662627 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge1_fmeasure": 0.2239773930782515, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.003099702038886262 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_precision": 0.08027601856562787, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0028587155748841155 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_recall": 0.12944258320105298, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0033520136379546575 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rouge2_fmeasure": 0.07459291610833325, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0021594277862978053 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_precision": 0.21029176429912327, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.003853857396675998 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_recall": 0.3046329495523381, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004807937355834806 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeL_fmeasure": 0.1924435416395898, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0026000922872309144 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_precision": 0.21773348211753543, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.004056669090372054 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_recall": 0.29668821393068523, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004287898580495838 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "implicit-graph-description", + "rougeLsum_fmeasure": 0.19609167052374815, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0027163034898814884 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d369b84e068b220cf72f3ad4bd1293a6dab4e25f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_precision": 0.03974548833329957, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0016187665175497782 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_recall": 0.14319286698789227, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002689949685516924 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_fmeasure": 0.051963445903168815, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001030164799332613 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_precision": 0.0032603459694508664, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00035703887248090323 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_recall": 0.015671514326625717, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.001194008851035889 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_fmeasure": 0.004924022976700059, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00046504584059277863 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_precision": 0.03627088781319514, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0015426070426077998 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_recall": 0.1339405385147445, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0025465644416711453 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_fmeasure": 0.04746954821622165, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008839674059173651 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_precision": 0.036598894332640367, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0015865773575606916 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_recall": 0.12773491888135802, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0022633071599434925 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_fmeasure": 0.04700320033377673, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0009162627771699139 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "bleu": 0.10593475044710148, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.02687963406061457 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.json new file mode 100644 index 0000000000000000000000000000000000000000..e3705c29433f7953eccce02944ed79eb100fbafb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_precision": 0.1735967063811906, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0026270802204174095 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_recall": 0.17887650999515012, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0031318162204511425 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_fmeasure": 0.15066523178744332, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001954438625710324 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_precision": 0.021433820753724266, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.001247407681297529 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_recall": 0.029129370749806007, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0016832821472482552 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_fmeasure": 0.01960777337004029, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001029143211904409 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_precision": 0.14613868593964888, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.002258852219739637 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_recall": 0.15296643190709636, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.002859088570123784 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_fmeasure": 0.12623806450553654, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0016066368664537727 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_precision": 0.15418999276855516, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.002386058978805089 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_recall": 0.15812304797391522, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0027464038170145967 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_fmeasure": 0.13299010686343601, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001711708966298464 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "bleu": 0.866182823458432, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.12067272006028423 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.json new file mode 100644 index 0000000000000000000000000000000000000000..27e8fe5fb8ab497e436c76dd9d96cad1a4662d09 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_precision": 0.18939988211510023, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.003015336802954258 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_recall": 0.21147314525622352, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.003724259557883497 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_fmeasure": 0.16765923923678647, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0022559374477986185 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_precision": 0.03379022133984764, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0017843702674752064 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_recall": 0.04784569405826686, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002202164940653821 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_fmeasure": 0.03131581713976908, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0014111826750632776 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_precision": 0.1598064546454118, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.002629394580363481 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_recall": 0.18237543607435028, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0034360872181296307 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_fmeasure": 0.14117220655320378, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018990556078266275 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_precision": 0.16876738068884203, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0027439682577306787 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_recall": 0.18685899221940896, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0032539799319502814 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_fmeasure": 0.14809597509839093, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001972913231852908 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "bleu": 0.8730659372849066, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.0967542162395743 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.json new file mode 100644 index 0000000000000000000000000000000000000000..500ccdbc0a370271657c548c0055fb22596c6438 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_precision": 0.20206518395397247, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0033815561981644514 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_recall": 0.22055576804184665, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0038689842229781995 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_fmeasure": 0.17604709161678792, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0024207021911546002 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_precision": 0.042414826534170676, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.002194212193720834 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_recall": 0.056638379731478804, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0024560943269569097 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_fmeasure": 0.03774742782188923, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0016476754720179338 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_precision": 0.17012750089049355, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.002909118143288585 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_recall": 0.19153932535514462, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0036627963511066176 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_fmeasure": 0.1484395491444522, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0020503728880959028 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_precision": 0.18026184477100235, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0030566342359595712 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_recall": 0.19503635904047142, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.00336915844462403 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_fmeasure": 0.15595031738973972, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0021234132418142156 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "bleu": 1.2329509109603611, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.17037107794770673 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8ec56b1dd7c4619faa038a7702aec97d34a2a611 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_precision": 0.21304666535883363, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0035447207581696576 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_recall": 0.24044196270498344, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0041272020875937985 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_fmeasure": 0.1877008682716093, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0025984841921980026 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_precision": 0.05150741153389857, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.002310685514094819 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_recall": 0.06873712069242928, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002686212129477722 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_fmeasure": 0.04618308258359416, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001794744112452255 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_precision": 0.18100550700598406, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.00309059853405147 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_recall": 0.2097555633903283, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0038640348862670876 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_fmeasure": 0.15952145174338822, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.002218483952497624 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_precision": 0.18979889801871716, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.003258591536788394 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_recall": 0.2114319997150186, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0035621450472765647 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_fmeasure": 0.16563209206374943, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002290227287484681 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "bleu": 1.0792721560875334, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.11897941335086845 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b28121ac1ea455bd4b918951724bde43909739bc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_non-explicit-description_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_precision": 0.22377177397658685, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.003751306840404075 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_recall": 0.24374911073515992, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004063940123637665 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge1_fmeasure": 0.1937895542833093, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0026930519639634374 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_precision": 0.05842395909971782, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.002544233000490118 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_recall": 0.07447247779662981, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0027180704781684995 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rouge2_fmeasure": 0.05181468037449851, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0019301208843236668 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_precision": 0.19087203826268628, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.003283058254228487 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_recall": 0.21393350174137546, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.003813517852998068 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeL_fmeasure": 0.16586855159557498, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.002321441985077457 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_precision": 0.2003884829724675, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.00343390307735665 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_recall": 0.21705758718159215, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0035797162130504407 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "rougeLsum_fmeasure": 0.17256400094312105, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002384598354184546 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "non-explicit-description", + "bleu": 1.0840527290308135, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.1285257175145367 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.json new file mode 100644 index 0000000000000000000000000000000000000000..8ef923bb33908f9786cbe63cbe2a7078a5231d4e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_precision": 0.11575198382455341, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0017409474424184654 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_recall": 0.608459061007921, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.003019908683780843 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_fmeasure": 0.1845095102209193, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0022693042573866838 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_precision": 0.04666714418190469, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0009925004787402806 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_recall": 0.25929817858149656, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0031405181722228706 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_fmeasure": 0.07462288276980816, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0013694868585983554 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_precision": 0.09923197095834116, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0012283545567891168 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_recall": 0.5587128288782699, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.003317057185320759 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_fmeasure": 0.16027950358425136, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0016115627858449338 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_precision": 0.09697095057432645, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0015588062714270727 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_recall": 0.5092192403982401, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0028311576287597846 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_fmeasure": 0.15437018471820735, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0020528117868010066 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "bleu": 0.80522341763869, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.08331054875537132 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.json new file mode 100644 index 0000000000000000000000000000000000000000..97f3d576f4abfabf60907e3ea53ab12406ee62bb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_precision": 0.19174924772721366, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0032940489896208926 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_recall": 0.2698784746776444, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004773612866682941 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_fmeasure": 0.1835504434103257, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002742918027631955 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_precision": 0.04272035087355504, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0019901580959531236 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_recall": 0.08265565051963014, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0030886698848430383 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_fmeasure": 0.04520576758964237, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0018353621819071602 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_precision": 0.1601819681970939, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0027461365015910427 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_recall": 0.23680658224270798, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004517480324960939 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_fmeasure": 0.15410415993634588, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0022370627269454606 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_precision": 0.16856045163213934, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.00294994820031969 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_recall": 0.2363719127409182, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004152500838774223 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_fmeasure": 0.16046862402135503, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002398180973300977 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "bleu": 0.9786465584605349, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.14122810214566986 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.json new file mode 100644 index 0000000000000000000000000000000000000000..c17cbd57584c44571a40b246e1da723a40812411 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_precision": 0.20221739794884294, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0035499636350329366 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_recall": 0.3332186264589581, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.005170101384807238 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_fmeasure": 0.1992879161350844, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002645957854064047 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_precision": 0.05936354342280888, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.002387647853920241 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_recall": 0.1225094044913992, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0034016962379593376 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_fmeasure": 0.06125938231479426, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0018555518510493417 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_precision": 0.1735345422105144, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.003136069929113322 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_recall": 0.29921178664666864, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.00498953624810007 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_fmeasure": 0.17221690830374237, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0022796430855117032 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_precision": 0.17949949840259782, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.003267322153420465 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_recall": 0.29229470206548336, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004488431177710736 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_fmeasure": 0.17513713323826788, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0023508381923365734 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "bleu": 0.8880569236257283, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.10425228469519156 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.json new file mode 100644 index 0000000000000000000000000000000000000000..29f47fe2c113cb3ff15881a3135d5bc226c30ece --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_precision": 0.22015440449805468, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.004191773103751877 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_recall": 0.36592032189171225, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.005068220370589984 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_fmeasure": 0.21408595760940946, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002783818736006089 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_precision": 0.07910542573583534, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0029902820037111502 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_recall": 0.1491354669018872, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003459225616571808 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_fmeasure": 0.07696626766564611, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0020398698531970743 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_precision": 0.19072950772310418, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.003726367705712794 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_recall": 0.33282521900185674, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004954398958565515 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_fmeasure": 0.18711621313587448, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0024249095985234463 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_precision": 0.1958992768265335, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.003884089051877238 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_recall": 0.3218771452899728, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004412820950063993 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_fmeasure": 0.1889169148591612, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0025246051964903276 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "bleu": 0.9859334350527383, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.09896199153842244 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.json new file mode 100644 index 0000000000000000000000000000000000000000..4897c214d9eaa88680df7952363c3fb6bd82e110 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_precision": 0.23228499942428968, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.004398241056245007 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_recall": 0.38453431214088857, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.005025202128638685 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_fmeasure": 0.22549673923508326, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002910775643802205 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_precision": 0.08911780913376037, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0031127641641959516 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_recall": 0.16391169232553854, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.003564158188179595 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_fmeasure": 0.08622184894243098, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.002115033774398341 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_precision": 0.20268160388419554, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0039238158298998795 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_recall": 0.3506485664858236, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004886831999021539 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_fmeasure": 0.19820026126581727, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.002503140302475953 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_precision": 0.20731340856698283, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.004088067992288368 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_recall": 0.33831857306922314, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004362271840091005 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_fmeasure": 0.19907520284773375, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002614354718088979 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "bleu": 0.970241931626179, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.09819030681966434 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.json new file mode 100644 index 0000000000000000000000000000000000000000..fda04542738f2d0a5f31cb895970d32280c11731 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-web_nlg_en_very-explicit-description_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_precision": 0.2382691545863073, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.004756985829441475 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_recall": 0.3912072250236538, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004984269579179742 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge1_fmeasure": 0.22840858338472744, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0030840481426459535 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_precision": 0.09843522450433298, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.003424552765398845 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_recall": 0.17269348031155235, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0035758918530598553 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rouge2_fmeasure": 0.09172527737837707, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0022023809206421522 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_precision": 0.20797653399558047, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.00422832319942412 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_recall": 0.35688189171657314, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.004844058830738807 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeL_fmeasure": 0.2006439166198059, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.002601338113671856 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_precision": 0.21340003515373943, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.004405460746761557 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_recall": 0.3469582914902356, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.004377091064495331 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "rougeLsum_fmeasure": 0.20278396643749147, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002742019476188682 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "very-explicit-description", + "bleu": 1.0632385816538097, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.108635681810979 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2b436c9a91291cd1fe1bee640587f2b6721bafcd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_precision": 0.195566960716181, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0019276846426063785 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_recall": 0.3533886371026647, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0027880868773002996 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_fmeasure": 0.23412884345862264, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0018096388944563407 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_precision": 0.04589459114508951, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0008493337249853646 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_recall": 0.08686815821286678, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0017485584142853405 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_fmeasure": 0.05530555190416877, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0009620765372106006 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_precision": 0.12997894688819828, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001176996687844147 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_recall": 0.2455653248515433, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.002216289748634435 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_fmeasure": 0.1577035391779481, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0011540548708147851 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_precision": 0.18107871658618507, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0017806857113047642 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_recall": 0.3283060348710063, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002625017894293712 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_fmeasure": 0.21698957847628453, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001673828218441473 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "bleu": 2.4682328449343904, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.07088258721604575 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..01da7122b8ac49a31946823a234289295edadd7b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_precision": 0.15627750165547535, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001962386369273289 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_recall": 0.2525742254443488, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.003113402494824898 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_fmeasure": 0.17453230736185904, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001969765354449983 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_precision": 0.029169479431573355, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0007882937343141538 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_recall": 0.0531848239381476, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0015457168877853818 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_fmeasure": 0.03409011634055016, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0008690874010719925 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_precision": 0.11201479367079172, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001306085160918015 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_recall": 0.1848814168046244, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0023307923443449947 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_fmeasure": 0.1250045596802973, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012753773488612319 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_precision": 0.14621744079984547, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0018210021156558275 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_recall": 0.23601641233060858, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0028953510119446627 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_fmeasure": 0.16303218310550338, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018145396789941985 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "bleu": 1.7919407346163008, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.0737452533520425 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..30850d292e4656da01ec40c7ad9dd7bff6974dc4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_precision": 0.14501437881859028, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0019433084591004713 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_recall": 0.22467032769033468, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0029784346495177407 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_fmeasure": 0.15863525455004393, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001916917232761661 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_precision": 0.02442996212535727, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0007519260848068276 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_recall": 0.042424873953699184, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0013993567734203126 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_fmeasure": 0.02797037755556898, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.000824659834492331 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_precision": 0.10658397240465457, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013324023033187138 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_recall": 0.1684211774861765, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0022097636904149756 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_fmeasure": 0.11668679312793952, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001279584145980854 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_precision": 0.1356637096139804, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001799350424574685 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_recall": 0.20992335195224027, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0027445156356427094 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_fmeasure": 0.1482203100115215, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0017644287180480047 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "bleu": 1.51129197235676, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.053033171757604795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..668ba4271a02ecb1b90ad9dba4859c3d11ade889 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_precision": 0.12488990987685827, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0022261432116102544 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_recall": 0.18139575994673116, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0030867748398314713 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_fmeasure": 0.12879034116675933, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002014213748068574 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_precision": 0.020587304073537236, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0008430364325238309 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_recall": 0.03345951804642443, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0013102881750652396 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_fmeasure": 0.02198351222980969, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0007661410803321813 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_precision": 0.09378166940289302, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0016774718846480157 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_recall": 0.1378319099477178, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.002341101765656631 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_fmeasure": 0.09609151005725931, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0014143522793016892 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_precision": 0.116314348038094, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0020844285519718204 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_recall": 0.16840969828764962, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0028496816197026674 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_fmeasure": 0.1195876958441179, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018550103716636955 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "bleu": 1.4186659295702861, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.050267910728881454 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..cfe0be4bcb6fe22e00d97b459694f1a5b6c5ece2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_precision": 0.04274798462927153, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0018161718038238448 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_recall": 0.05867994619730172, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002374781099841643 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_fmeasure": 0.04085144274673853, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001538442204027294 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_precision": 0.006984195242455265, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.000603809740571673 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_recall": 0.011817282399442079, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009217929633034777 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_fmeasure": 0.0071615346459846605, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0004694288024279032 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_precision": 0.0331311683624868, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001416652850979173 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_recall": 0.04606968779468327, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0018746567174795128 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_fmeasure": 0.031403237162404916, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0011428460910517797 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_precision": 0.039597785262755085, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0016586096902770702 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_recall": 0.05473786135131624, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0022121499800027366 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_fmeasure": 0.03803522378880029, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0014259840855105786 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "bleu": 0.18764755097372476, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.0204323879125267 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..3ebd8146cd6321e3579e4e0fef320baa6fa3e5f9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_article_summary_en_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_precision": 0.006928543414105365, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0008521915511742353 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_recall": 0.00867185146550297, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0010332808843393272 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge1_fmeasure": 0.005950641245994375, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0006411674676836966 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_precision": 0.001396425548191038, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0003008386819272615 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_recall": 0.0020329927104609604, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00048577777702315096 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rouge2_fmeasure": 0.0011656375598739542, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002028046057963131 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_precision": 0.005494500329872309, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0007044489282665799 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_recall": 0.006910731196408219, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0008474442564134671 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeL_fmeasure": 0.0046037610582904, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0004842752495293122 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_precision": 0.006515436893618955, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0008141521585116435 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_recall": 0.008010452744131268, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0009551600048254268 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "rougeLsum_fmeasure": 0.0055130820845512825, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0005938752458158761 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "article_summary_en", + "bleu": 1.2081769471696679e-09, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 4.7758554492272945e-09 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..95844d65b4916eb769ce3fac9b9cd7a1704a7249 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_precision": 0.10569868627384524, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0017140526493108679 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_recall": 0.16204648662100252, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002316216467829637 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_fmeasure": 0.1174568672178565, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0016459536455676414 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_precision": 0.013201893034513962, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0005378682826493545 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_recall": 0.022027771467537875, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009738896413116423 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_fmeasure": 0.015045420297771185, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0005981449989858111 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_precision": 0.08838578365243173, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013067594648947581 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_recall": 0.1392947948040508, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0019179440859143518 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_fmeasure": 0.0992022930965774, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012654116495173472 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_precision": 0.09855134328369819, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0015934085607222398 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_recall": 0.15144176964309033, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002157349066143636 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_fmeasure": 0.10959697102431157, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0015286108227936896 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "bleu": 0.8117389101795618, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.05120531843865198 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..75f2255b845707a343bc20709d253ea964da2ff1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_precision": 0.11390300359943901, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001505310086956201 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_recall": 0.11050639157282433, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0014435125389142748 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_fmeasure": 0.098994814039191, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0011402494962994437 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_precision": 0.004517191185289906, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0002871310006425094 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_recall": 0.004113881151457014, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00027381193246220814 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_fmeasure": 0.0038137867450023814, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00023343889478032686 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_precision": 0.09172939994661446, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011916256374520841 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_recall": 0.089104978321703, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0011511611569130506 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_fmeasure": 0.07918587597477968, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008565313092324011 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_precision": 0.10993079553359293, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014392346467215847 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_recall": 0.1069392153189123, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0013956438936564995 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_fmeasure": 0.09563169367500524, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001091436945649962 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "bleu": 0.2794013007287592, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.04394092663556765 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6d8aa6d5b3997e36b7b1047046883561a736d7fb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_precision": 0.11467425239533192, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015225012916013473 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_recall": 0.11441629521647928, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0015727059489721053 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_fmeasure": 0.10072739595349496, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0011867245098453186 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_precision": 0.005508580331675803, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00035383861846697813 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_recall": 0.005934869967984835, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0004322756043539301 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_fmeasure": 0.004828784168441771, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002759061972464504 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_precision": 0.09149413336589454, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011975294685730132 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_recall": 0.09135200468914431, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0012290284607197216 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_fmeasure": 0.07966550478447607, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008671984140603575 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_precision": 0.11056182525730968, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014655410176995765 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_recall": 0.11035544182626898, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0015086333978719083 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_fmeasure": 0.09709883418158977, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0011361943688270538 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "bleu": 0.3628903862281783, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.040600834550736854 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..59cf29d5a66a9e1bf063d45b111ee74fdbf6ce4d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_precision": 0.09881225588094651, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0017794429029784138 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_recall": 0.0961080094935916, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001760024204009069 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_fmeasure": 0.08360995103143794, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0013441180625539642 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_precision": 0.0059206327308198945, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0004468897050553651 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_recall": 0.005917242814787239, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00045428975938505313 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_fmeasure": 0.00494689889012699, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00032931853157837956 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_precision": 0.07953381242832525, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001428896234358919 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_recall": 0.07718976821843865, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0013856069309638303 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_fmeasure": 0.06662277406174887, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0010213036544403373 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_precision": 0.09515792843426966, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001709487622838808 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_recall": 0.09256568091207279, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0016852915566244572 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_fmeasure": 0.08045562840916225, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0012855845245021166 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "bleu": 0.3640822400959341, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.04928248150151389 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..36045706a9683edad3fa61d3d4e8c6864211d63e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_precision": 0.0317245796662674, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0013705699322416266 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_recall": 0.03146018864612653, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0014391156321984263 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_fmeasure": 0.02596269332900368, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0010634101020032597 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_precision": 0.002339551167089779, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00030256564830245586 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_recall": 0.003101162831484645, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0004679085866658427 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_fmeasure": 0.0019833072972918566, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002144425508793813 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_precision": 0.026049745321603573, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011243334623461175 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_recall": 0.025594964978776304, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0011360606064423507 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_fmeasure": 0.020998319543683103, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008262281758861216 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_precision": 0.03023574490650669, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0013013309198418228 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_recall": 0.029726826443738044, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0013382698786662225 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_fmeasure": 0.02460219706818639, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0009968526836547482 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "bleu": 0.022070239323623318, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.009020956658967978 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..fa754093c56ae439adc59e17aa8818cf1a64246e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_rephrase_en_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_precision": 0.004997411592452321, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0005839652233329812 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_recall": 0.00516993867487459, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0007131741906943778 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge1_fmeasure": 0.004061499208353005, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.00046516835238848473 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_precision": 0.00030964206877279654, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 8.927954397265049e-05 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_recall": 0.0005971005703343351, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00021977639166152163 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rouge2_fmeasure": 0.0002762510614131578, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 7.152448161217703e-05 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_precision": 0.004026290704976211, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.00046120664542663453 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_recall": 0.0042081128532273256, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0005776147810982953 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeL_fmeasure": 0.003257613603154482, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0003601612804489262 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_precision": 0.004781410549830059, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0005638818969053312 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_recall": 0.004893422518392296, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0006832059638435896 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "rougeLsum_fmeasure": 0.0038410375028680617, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.00043981063385292154 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "rephrase_en", + "bleu": 1.2772835382495755e-13, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 3.981569081927512e-12 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b7fd553298f4dcc14f5c1f9d168ece6b5bf9eaf3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_precision": 0.05321505980023667, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0014181666167610405 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_recall": 0.07795628718339453, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0018410017875166815 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_fmeasure": 0.05817807410278456, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0013730134887578534 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_precision": 0.004212936258690241, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00028227201371374533 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_recall": 0.006550413011055106, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0005770046318012553 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_fmeasure": 0.004598565155715411, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0003111709286716547 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_precision": 0.05005075628972684, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001278959345154331 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_recall": 0.07412927953859504, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0016956652339899909 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_fmeasure": 0.05496385663485581, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012393700178193036 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_precision": 0.04982130748814443, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0013143803339713488 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_recall": 0.07363722344726391, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0017324048141738725 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_fmeasure": 0.05462669247662518, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001271676260318409 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "bleu": 0.2519277717730189, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.03524949351036431 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..07ab46867d32ffcf90fab35588c461a4095f2205 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_precision": 0.11385785104351803, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0014965391184321181 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_recall": 0.10937667766926965, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0014145590881837738 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_fmeasure": 0.0987597492588469, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0011303207925802167 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_precision": 0.004457883873596226, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0002826935523898672 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_recall": 0.0040283569854367126, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0002662158979064575 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_fmeasure": 0.003733269944172192, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002255133736408092 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_precision": 0.09155580309452313, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011764557134249975 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_recall": 0.08815903146004761, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0011271831761762122 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_fmeasure": 0.07895189836522858, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008476363984155375 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_precision": 0.10994991245043519, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014301005338092242 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_recall": 0.10592427428936108, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.001368238986007311 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_fmeasure": 0.09547883528709802, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0010834332898652644 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "bleu": 0.23894215568211405, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.0231127989782631 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..07af15816507b90a5dcbbd933f18d625b458e6bb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_precision": 0.1163150797172004, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015925911586497405 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_recall": 0.11665631687345931, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0016340035824879626 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_fmeasure": 0.10225814979631906, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0012292507820030408 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_precision": 0.006595299157223728, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0005108250821972147 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_recall": 0.006811278906280594, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0005095210834151304 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_fmeasure": 0.005602755335977656, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.000365207226287633 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_precision": 0.09346370560850872, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0012527414348738914 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_recall": 0.09379022195144442, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0012826081895714718 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_fmeasure": 0.08152225050163284, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0009069898459798317 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_precision": 0.11220025027683658, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0015289183398502308 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_recall": 0.11254662956683745, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0015531537080274286 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_fmeasure": 0.09858585234149649, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001170030683997042 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "bleu": 0.4379392770159711, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.059428018607743945 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..6d75871676aba4a318d9810384e284bf75d7d948 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_precision": 0.10060948026044556, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0018664954448892226 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_recall": 0.10197302779012452, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0019812796311759295 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_fmeasure": 0.08654940806312904, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001431495451108354 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_precision": 0.007376831208587836, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0005437291438342406 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_recall": 0.008673705432290764, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0007007938800809519 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_fmeasure": 0.0065193989842291565, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00042504340054855125 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_precision": 0.08088970368544203, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0014724520083722664 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_recall": 0.08233682962107754, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0015887611692809386 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_fmeasure": 0.06915495549341871, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0010949721512951217 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_precision": 0.09635575140755301, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0017746806567606403 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_recall": 0.09756525164753817, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.001879769069025684 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_fmeasure": 0.082797340411407, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001354438253975997 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "bleu": 0.5442256675776663, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.037604550641844786 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..248a363e225d112167c3477917a555004e195c6b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_precision": 0.03285278805076312, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.00151492862638139 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_recall": 0.033499707980673206, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0015787383836412087 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_fmeasure": 0.02705120556648003, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001128461395321214 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_precision": 0.003253495732258925, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00040392310255452183 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_recall": 0.004071265417854878, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0005813660435076962 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_fmeasure": 0.0026853344180586664, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002789624736107807 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_precision": 0.027230939273538826, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001255620650530008 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_recall": 0.02759081624466607, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0012884449077523894 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_fmeasure": 0.022141442290806702, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008958829005211576 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_precision": 0.031233183019105354, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014213211972707832 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_recall": 0.0319845426682248, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.001491847145002001 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_fmeasure": 0.02576886539837896, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0010599565782314143 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "bleu": 0.027510143284592198, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.005850102428249243 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..dbeaac5b607601f912f7fed4bb228a19f9bc9472 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_summarize_above_en_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_precision": 0.005131645813217702, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0006494612556736446 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_recall": 0.0046603087139718904, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0005994833560269134 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge1_fmeasure": 0.004055948100688518, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.00047821717141908343 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_precision": 0.0006565696469248757, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00021376994443478634 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_recall": 0.00046749083156390686, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00012176761634464935 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rouge2_fmeasure": 0.00042158314099139017, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00010671999988396933 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_precision": 0.004234119839442783, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0005284078757495208 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_recall": 0.00396076135348473, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0005103337395972377 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeL_fmeasure": 0.003372046824276411, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.00038942868804587514 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_precision": 0.004974502856539407, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0006280274207578934 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_recall": 0.004513499194743017, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0005832210379541333 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "rougeLsum_fmeasure": 0.0039257863548093274, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.00046232884670699545 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "summarize_above_en", + "bleu": 3.9529978759982985e-15, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 1.548319477203052e-13 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..39364770de016e9c7486c6cf14a5bfd12065adcf --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.1078207522843226, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001940682197702513 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.1520153396969911, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002277894036435405 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.11334607060168528, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0016396098775080439 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.011837859560447648, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0005138331303314764 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.019458716329622143, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009420647807959251 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.013280003159457142, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.000558295558429676 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.09180182708936059, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0016152505728822433 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.13192962900825583, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0019204374301591803 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.09699392119251118, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012980799468792427 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.10116224232784549, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001831498246711715 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.14236722673055757, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0021081023222958317 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.10617032427066436, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0015161029623370764 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.6707270817884038, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.046602035483089825 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..06348965ae07fc4ffb812a4e31e65f6af3d51427 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.1160224630989691, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015635722100785284 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.11479872451661574, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0016007866744804707 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.10140750562931955, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001200027323440739 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.005941589755812423, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0004274156364302611 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.006017596275684403, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00041646260466011385 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.00507966104363529, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00030717988724990536 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.09349045000409738, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0012461235636124553 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.09234699285193011, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0012589640727499547 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.08108861724066418, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.000902890435608752 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.11197455431954438, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001497949074925301 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.1110141699775543, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0015424239322369367 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.09791498603078132, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001146504425053145 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.43855817321834095, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.06688374272014054 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6c0f4585f75716165c1c806555ee2098b96b44d9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.14110589305024318, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0022270422789620343 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.1403877205314885, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002190793145077092 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.11933695488013622, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001559164548856994 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.016440629225865595, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0008773719234169698 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.01682561907914257, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0008426407227716545 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.013472946625192286, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0005971595008055532 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.11303183510467564, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0017832927124786565 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.11265616862637728, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0017655005819091217 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.09470570644133551, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0011669855247486087 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.13426932254715146, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0021052543187055337 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.13349014172459456, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002067397596426611 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.11342531741430635, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0014614019347966196 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 1.0367136986637764, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.10294385360100548 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..0cee2ff62870ad9f3844cbe4e4d8dca0ecf12174 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.1432248072165103, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0028194048557081534 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.1235766277421485, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002354909584881938 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.10845969305714753, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001764500717605624 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.02165017024117859, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011383917848863225 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.018904933463519274, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009796659633542278 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.015547635018168346, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0006704388234796883 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.115448783961469, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0023052494207092614 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.09991818086293902, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0018968351003013303 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.08660256700931251, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001347993958631469 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.1347230613061051, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.002655304240899613 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.11587053571503414, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0021893808381981995 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.10174661203721236, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0016381663427203297 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 1.0055082276927305, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.07192737514794537 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..0df250fe43772a78faed289bafd9892a00f6db79 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.05608048532310048, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.002435498849231569 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.041593600839943914, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001788014682833587 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.03803967268390006, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0014747568915058733 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.011745234816576059, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0010829411163804264 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.007380582194532306, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0007127969246877938 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.006755300956624583, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0005462948561714105 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.047091703984391005, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.002065424301205954 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.034604035967383255, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0014944258543141873 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.031443909785773674, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012099672207623704 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.05323231626482197, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0023275252393686156 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.0391023340007786, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0016636743475211388 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.03593453392452451, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0013935406055845413 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.0464769949251449, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.005281612141215288 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..391194821ca5e8caacff1f4b71d1d75a5e3f43b0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_tldr_en_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.009319821178210992, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0010269796471685194 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.007261443669465562, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0009201674527650682 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.006408772411533697, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0006726664225328778 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.0015883326473273408, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0003471561820758166 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.0016746964377212603, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00043827050828643875 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.001215199948152673, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00024366601487357684 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.007922705066461089, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0008728161809959782 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.006196890284199744, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.000796669253101562 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.005446190005924919, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0005737856458351668 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.008783315274046653, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0009687512562761863 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.006837799638085168, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0008734893361383668 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.006002979726182862, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0006246362092905004 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 7.71421931319727e-14, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 4.575898076497286e-13 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b5aa04eb2b805c99c6f62c08656cd68d56e60757 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_precision": 0.1467073059254317, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.003923847788182457 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_recall": 0.1488423584822216, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002514278160277046 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_fmeasure": 0.11287104782454531, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0018302548422649888 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_precision": 0.015139213553420103, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0006017762732827434 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_recall": 0.023991338309341914, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0010741770192485198 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_fmeasure": 0.0168939526317488, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0006560231719498498 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_precision": 0.12846108969943054, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0037967129632843506 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_recall": 0.12514947700874288, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.002011926521503057 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_fmeasure": 0.09354722719833262, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001367594008196884 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_precision": 0.13919269715957514, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.003880077948366859 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_recall": 0.13851578235021383, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0023319716005974654 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_fmeasure": 0.10483417861156145, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0016823495491907201 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "bleu": 0.8049467835361911, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.06125790470590714 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cc357257cc53a77494598a69c888bf1c91aa035a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_precision": 0.11672921172744681, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015455078946896611 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_recall": 0.12404651186718361, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001833482506124768 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_fmeasure": 0.10581662192060133, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001297467104327135 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_precision": 0.00662318107917187, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00038908144611155763 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_recall": 0.008569619519959264, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0005860808060358155 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_fmeasure": 0.006578200350543033, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0004020452136350789 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_precision": 0.09258137259929677, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011789964767188995 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_recall": 0.09781932700181184, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0013635799564556685 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_fmeasure": 0.08315064354847855, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0009263412660918235 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_precision": 0.11236796963847627, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014661420025751913 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_recall": 0.11962539469182883, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0017515297053630175 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_fmeasure": 0.10191075189261449, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0012281012231510622 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "bleu": 0.6042770786450469, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.06784193000730189 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1940d8fdfc3d363bcc8dddb1ab6c1cfeff3d7e82 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_precision": 0.11791706075978581, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015994717296165192 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_recall": 0.14298806278491627, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0020625427368130608 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_fmeasure": 0.11408900626000608, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0014182183684096998 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_precision": 0.008285813515207935, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0004549347251757663 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_recall": 0.012254279196802272, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0007733247902712675 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_fmeasure": 0.008686912843235644, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00045294754346949324 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_precision": 0.09043062219460844, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0011743927829203635 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_recall": 0.10998900310161605, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0015428002199032057 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_fmeasure": 0.0867863689660142, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0009676979999670107 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_precision": 0.11235660105208539, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001507091449296961 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_recall": 0.1359188111061881, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0019151506035573415 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_fmeasure": 0.1085601417082136, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0013181344740805481 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "bleu": 0.6359039546247384, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.05332890289165686 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7566840133d3a028e634b1ce286690e375fdf1d6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_precision": 0.09005735863253914, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0017410925572476383 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_recall": 0.11209657560256954, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.002246234879953545 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_fmeasure": 0.0863434945247995, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0015282100730080173 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_precision": 0.006965462874923481, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0004357269928233993 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_recall": 0.01068806664642742, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0007581392108308288 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_fmeasure": 0.007238486310418053, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.00042895291336820845 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_precision": 0.06963288035102946, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0013235845589289316 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_recall": 0.08642316047519256, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0017071161351831217 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_fmeasure": 0.06590039763154197, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0010964007554027833 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_precision": 0.08570933352018638, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.001644764365928756 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_recall": 0.10632118573218488, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002114071365640021 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_fmeasure": 0.08200533326129804, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0014384128001919997 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "bleu": 0.5690290357096291, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.08303885182927963 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ebba2fc01e959ae4acf8ee5cf8e15285145744a6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_precision": 0.02299224348433701, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0011412033083596786 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_recall": 0.030086106435386208, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001556085408646244 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_fmeasure": 0.021738632248596658, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0010230448733526455 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_precision": 0.0017495363473227336, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00020151602411722723 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_recall": 0.0032970556699345034, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0004918025374367564 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_fmeasure": 0.001875948079941924, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.000219572547682823 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_precision": 0.01828959837223259, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0009017986426573455 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_recall": 0.024055207310948443, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0012481605588282325 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_fmeasure": 0.01708346323437329, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0007728353496458206 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_precision": 0.021695271758735132, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0010708297762772132 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_recall": 0.028324718060384762, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.001443357150753234 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_fmeasure": 0.02048581320979614, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0009585758119225723 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "bleu": 0.016816379280954568, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.0028919321680318318 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c5e2426150cbacc425cdabc545d2ef8db1bb9798 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_GEM-wiki_lingua_en_write_abstract_en_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_precision": 0.0023192080637707735, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.00038854174236947536 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_recall": 0.0037156411516436165, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0006659054396004237 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge1_fmeasure": 0.0023847991624654733, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.000384610434523063 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_precision": 0.00024483684853279374, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 7.040995395638042e-05 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_recall": 0.0005891611955524744, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00018205158176419917 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rouge2_fmeasure": 0.0003122235342379389, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 9.229879998061021e-05 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_precision": 0.0018119271192860117, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0002971679095161747 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_recall": 0.0028628954473527285, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0005077613704836201 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeL_fmeasure": 0.001821148625234418, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0002799930215985291 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_precision": 0.002232415013733976, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.000374058105161406 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_recall": 0.0035504517322428614, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0006368246151758458 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "rougeLsum_fmeasure": 0.0022835778404728443, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.00036781738986975464 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "write_abstract_en", + "bleu": 1.1597815660645416e-20, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 6.856426087822371e-20 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..0c6cfea02078718fad3a9fdeb3a6eaf6fb4d9c9c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014865395385928376 + }, + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc_norm": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014910846164229856 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..428cd4c9f6b4f2452ebcde839b551fc37f7643e6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc": 0.334, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.01492201952373296 + }, + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc_norm": 0.328, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014853842487270334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6095262c35eec8955e622fe324629a35876e9acd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc": 0.363, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015213890444671288 + }, + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc_norm": 0.354, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015129868238451772 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..724668d1cb739bfb656f50fd8e8bf70883ac988e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc": 0.355, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015139491543780529 + }, + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc_norm": 0.339, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014976758771620335 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..440e1e0830d71ea5963827c0b58d15fe6b319251 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc": 0.348, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.01507060460376841 + }, + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc_norm": 0.354, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015129868238451773 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d2f6e4f2b1dd49b931d994ec1354e5d72a69f60b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_GPT-3-style_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc": 0.352, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015110404505648658 + }, + { + "task_name": "anli_r1", + "prompt_name": "GPT-3 style", + "acc_norm": 0.355, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015139491543780529 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..42806921d6a09a1b25c3c65e761102b1fc596efc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc": 0.331, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.01488827258820393 + }, + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.32, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01475865230357488 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..50b2d50631f0a4c4368ff73cb76453ff5f1dece7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014910846164229863 + }, + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014910846164229863 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a5f13d56a099c1c6c729743e9c2e8c8bf4db9e1e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc": 0.339, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.01497675877162034 + }, + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014910846164229864 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..b39cbf1f47ea69ba9113c39b9193b3ce542a57af --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014865395385928367 + }, + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.332, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014899597242811485 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..4ca1202d4390aa5a5ebf5b7af19d7c4ba73c877c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc": 0.327, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014842213153411244 + }, + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.325, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014818724459095524 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4bc7a8e9b89809645163b75d9ce2007c497cd995 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_MNLI-crowdsource_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc": 0.308, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014606483127342763 + }, + { + "task_name": "anli_r1", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.302, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01452608023545955 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..8161db32c3946fb58c57e72880fe4a412b8a39dd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc": 0.336, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014944140233795027 + }, + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc_norm": 0.346, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015050266127564438 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f5929af35de52ba622737e66a0ea871f3e709890 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc": 0.331, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014888272588203933 + }, + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc_norm": 0.338, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01496596071022448 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..bf0b1b8567dcc4e0017c3edbf9ca5ef87d44de7d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc": 0.353, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.0151201726054837 + }, + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc_norm": 0.354, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015129868238451772 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..528561b66462c1eb0e5e6e8d37efe62008b6f14d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc": 0.35, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015090650341444236 + }, + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc_norm": 0.335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014933117490932575 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c329846a3a75eab572437a9389ea5a64a9db1d04 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc": 0.335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014933117490932577 + }, + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc_norm": 0.344, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015029633724408947 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..71f543a65717320812babae90a8e0c51694ef122 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_can-we-infer_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc": 0.342, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015008706182121728 + }, + { + "task_name": "anli_r1", + "prompt_name": "can we infer", + "acc_norm": 0.334, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014922019523732958 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..218fa968e6e824666b7461efd8f453ad363d381d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.324, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014806864733738863 + }, + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.332, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014899597242811475 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c6fd2dede69c5c998d61d3afecd0dc3d837ff5ed --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014910846164229863 + }, + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014910846164229863 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..82da0ea7080196d264021d7e1a0b72ce98c5ee22 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.348, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.01507060460376841 + }, + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.348, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01507060460376841 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7d47f03ae5c0ccde4fec727aa0041bff789710b4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.35, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015090650341444233 + }, + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.35, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015090650341444233 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..5fbdda7068262caa0335923660e291b56a0114fd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.325, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014818724459095522 + }, + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014933117490932579 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..95c54c2b6ff1a03212e30d18adcc12b18644a58f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_guaranteed-possible-impossible_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.328, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014853842487270334 + }, + { + "task_name": "anli_r1", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.327, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01484221315341124 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..209f396c3f6aa229a513fff5a036e830e73ee54a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014910846164229875 + }, + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc_norm": 0.355, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01513949154378053 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..db7ef38ab12acb5309a5e13d102a3303b9754ac1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc": 0.332, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.014899597242811485 + }, + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc_norm": 0.336, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014944140233795023 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..2eab051be92d8f5274246cc5f29c83ba1db2b9c0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc": 0.353, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015120172605483703 + }, + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc_norm": 0.354, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015129868238451772 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..caf5a428a28a6384b0a53a781480b4d6faafecec --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc": 0.346, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015050266127564433 + }, + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc_norm": 0.331, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.014888272588203931 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..07b19c35ed74cf3a28816e722f5816f9198dd23d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc": 0.345, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015039986742055235 + }, + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc_norm": 0.355, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.01513949154378053 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a30dd3d9acc6c05e16bf111714d45b12bac55da7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r1_justified-in-saying_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc": 0.344, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_stderr": 0.015029633724408947 + }, + { + "task_name": "anli_r1", + "prompt_name": "justified in saying", + "acc_norm": 0.343, + "dataset_path": "anli", + "dataset_name": null, + "subset": 1, + "acc_norm_stderr": 0.015019206922356953 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..de6d736120c03a7f0e0b385aa0d7fe8c836988c8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc": 0.32, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01475865230357489 + }, + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc_norm": 0.342, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.015008706182121734 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..8e99372bff5a69e37c47fcf5fc914aec83891d5d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc": 0.321, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014770821817934647 + }, + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc_norm": 0.315, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014696631960792506 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..203f835c5f906a6736733a908621a6b53926f1a0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc": 0.33, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01487687202745673 + }, + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc_norm": 0.326, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014830507204541028 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ca92bdd8923637fb7ccab361cd60ee67f8ea504c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc": 0.321, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014770821817934649 + }, + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc_norm": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014865395385928369 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c8abd1aa9afa81d9b0c2a5b9c871243bd56cfeb4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc": 0.327, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014842213153411239 + }, + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc_norm": 0.318, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014734079309311901 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..395294ec3dfbb53e470df59076102e00913125a6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_GPT-3-style_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc": 0.337, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014955087918653591 + }, + { + "task_name": "anli_r2", + "prompt_name": "GPT-3 style", + "acc_norm": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014865395385928373 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..ec927067b0f738ed4048a988a7b94fd62a00e89a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc": 0.339, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014976758771620342 + }, + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.323, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014794927843348642 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d19b52fcf689934f7b2313863e0aab0366f4aac5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc": 0.315, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014696631960792506 + }, + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.315, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014696631960792506 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..c05df40b37e001b140f061bba8e099f3edcf6e22 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc": 0.327, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014842213153411237 + }, + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.327, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014842213153411237 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..e73ee42bb4827a53134a0673597fb69c45fe608a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014865395385928367 + }, + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.327, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014842213153411242 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..91a59920e60be8afd5cce9d4402f9edb2a9aaa37 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc": 0.305, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01456664639466438 + }, + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.311, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014645596385722692 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..6d0f732aa3344bf4bfd3de8a37c991bd648254af --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_MNLI-crowdsource_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc": 0.313, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014671272822977892 + }, + { + "task_name": "anli_r2", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.317, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014721675438880233 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e0acfcfc1ec18f4fe38bdc73fa62fdfe9f793a74 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc": 0.33, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014876872027456729 + }, + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc_norm": 0.336, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014944140233795023 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..293569df20affef195f9d0f86404eda00be95521 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc": 0.325, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014818724459095524 + }, + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc_norm": 0.32, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014758652303574886 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..fbbaf74aaac0e72238418d4bdaff2e2b806deb48 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc": 0.326, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014830507204541031 + }, + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc_norm": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014910846164229873 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..84a4bba8984aec1e051576bf535224ea3555a1a1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc": 0.312, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014658474370509014 + }, + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc_norm": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.01486539538592837 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..59020a40fe72ab0bbc3a014f5b576728c58cc066 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc": 0.316, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014709193056057134 + }, + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc_norm": 0.318, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014734079309311901 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c4ef2d9e4a53792a15e270485d56beaa7354330a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_can-we-infer_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc": 0.326, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014830507204541033 + }, + { + "task_name": "anli_r2", + "prompt_name": "can we infer", + "acc_norm": 0.334, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014922019523732954 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..dcf827ec82b910e4686d8a1b3aacc53f0e955a91 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.334, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01492201952373296 + }, + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.332, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.01489959724281147 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..446b3df428baa58a0ef6f235de4a0d27ea7fcc3b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.315, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014696631960792506 + }, + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.315, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014696631960792506 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..c2e053a40d33c817fba223d2bb97c3053e042594 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.321, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014770821817934649 + }, + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.319, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014746404865473477 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..529e88c2c6a1a34322f209eedaf7092dced34641 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.296, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01444273494157502 + }, + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.297, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.0144568322948011 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..45b8cc02fca9016b7ee1c4357d6f0e47757d53b2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.316, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01470919305605712 + }, + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.311, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014645596385722694 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..88bcb5c102ae231c602c87206f707717b24c1893 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_guaranteed-possible-impossible_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.325, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014818724459095524 + }, + { + "task_name": "anli_r2", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.328, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014853842487270334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2c7e1fabc6c712fb3e5ff2ef551d59346d36d410 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc": 0.333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014910846164229873 + }, + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc_norm": 0.338, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.01496596071022447 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..bff8417ebda5ca50d9fde167f454f06611afe409 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc": 0.324, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.01480686473373886 + }, + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc_norm": 0.321, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014770821817934647 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0e386aea9d1e5000fdcc4f3972cd032f56929fc8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc": 0.328, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014853842487270334 + }, + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc_norm": 0.331, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014888272588203928 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..bfdc220d25413ff85e12833b681fecf1138fca39 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc": 0.318, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014734079309311901 + }, + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc_norm": 0.318, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014734079309311901 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b8b3ac48ea2834395706425487f32be865d92e7b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc": 0.314, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014683991951087978 + }, + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc_norm": 0.328, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.01485384248727033 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c0d62034ceb22c83cd6078616acaf15c3f439591 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r2_justified-in-saying_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc": 0.329, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_stderr": 0.014865395385928369 + }, + { + "task_name": "anli_r2", + "prompt_name": "justified in saying", + "acc_norm": 0.338, + "dataset_path": "anli", + "dataset_name": null, + "subset": 2, + "acc_norm_stderr": 0.014965960710224468 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e8eaad1c4e6947c0df728a5f556b10b7a60d2a0a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc": 0.30416666666666664, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013286140243317441 + }, + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc_norm": 0.3416666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013696658778002519 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..2518146a4f827a09c431d72f1cd091dad12c1c92 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc": 0.3433333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.01371263383046586 + }, + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc_norm": 0.3375, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013655897185463657 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e8d8b32293c95b5468f9bdc17415c7cea3712134 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc": 0.335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013630871843821465 + }, + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc_norm": 0.3383333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013664144006618261 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..572db573cdb07950ea448490d64360627f304621 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc": 0.3541666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013811933499570954 + }, + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc_norm": 0.35583333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01382651874849331 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ba1db1e2c646ec1eda8c39373bcd70eeb9bb21b6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc": 0.34833333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013759437498874072 + }, + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc_norm": 0.32416666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013517438120881617 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..995f9bb22c81cb96716202729f6e974d37a9dbd3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_GPT-3-style_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc": 0.32916666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013570806258433628 + }, + { + "task_name": "anli_r3", + "prompt_name": "GPT-3 style", + "acc_norm": 0.3225, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013499258621103247 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..0f19197824e90e2bc663b66f92f79622bcdb9223 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc": 0.3358333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013639261190932873 + }, + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.33416666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01362243481313678 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..35e938ca15d9d327a86a49d36e6c567c461acabb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc": 0.33666666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013647602942406393 + }, + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.33666666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013647602942406393 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..8e623487f83b493f95d91c6df1e3086a5e3feef7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc": 0.30833333333333335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013336721143136469 + }, + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.3075, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013326707242912048 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..42a950af5e1252dce6006426ec90cd4db01e5567 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc": 0.3308333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013588208070708999 + }, + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.32416666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013517438120881636 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..308026963d25271abba5a3aff12c03e78f123fd2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc": 0.32916666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013570806258433628 + }, + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.3283333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013562032919529019 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..f6239fb53f2efd81bd91b257ce440c95c94533c2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_MNLI-crowdsource_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc": 0.29833333333333334, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013213160837301237 + }, + { + "task_name": "anli_r3", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.30833333333333335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013336721143136467 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..13d149375ab1f3e166e1b036386b4513bb87cc2a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc": 0.3233333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013508372867300217 + }, + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc_norm": 0.3333333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013613950010225613 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..9f34a0e637433bc3ec1e1fbabfa8eb31ffd05ece --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc": 0.345, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013728421539454876 + }, + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc_norm": 0.3408333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013688600793296934 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..42ee6ea0eb54c98679b4c4f7725c31d61fd01a55 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc": 0.3275, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013553211167251953 + }, + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc_norm": 0.32666666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013544340907003665 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9c5001ae54fa54f78d006e79da4ed64a1b31ea8b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc": 0.3433333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.01371263383046586 + }, + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc_norm": 0.3525, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01379716491891836 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..f7acf89949c7699792cdbd18d7529d9b61265430 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc": 0.3466666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013744022550571942 + }, + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc_norm": 0.33916666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013672343491681808 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e122d969c42c6489ccd57cf263ee52d6f4331332 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_can-we-infer_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc": 0.3308333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013588208070708992 + }, + { + "task_name": "anli_r3", + "prompt_name": "can we infer", + "acc_norm": 0.3258333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013535422043417466 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..20ee72287fee9d1025f9dadf05e643fb34313507 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.32916666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013570806258433628 + }, + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.33, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013579531277800918 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..0b03513e9244d253cb8396a2a9f518b459fe4a1f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.33666666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013647602942406393 + }, + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.33666666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013647602942406393 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..8996c307e403da846f9f6d0ce61cf9a41a1313e9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.31333333333333335, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013395739415639082 + }, + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.31, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01335659633120026 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..5e9205e823f4c00b2fa4709bf5a928a87a2a010d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.32, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013471620929769142 + }, + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.32, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01347162092976914 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c9e28a71b55f9d0c3bf66f0b56f17dcb3aab66be --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.3175, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013443538681348052 + }, + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.31833333333333336, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.0134529489969963 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..4fb22e854f5103fa1e21e8d98fa0d608c7f43279 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_guaranteed-possible-impossible_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.31, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013356596331200258 + }, + { + "task_name": "anli_r3", + "prompt_name": "guaranteed/possible/impossible", + "acc_norm": 0.31166666666666665, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.0133762687909821 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..6c66b298d10d2bc57649b3a89bf6fccf34ee2be1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc": 0.33166666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013596836729485159 + }, + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc_norm": 0.33416666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01362243481313677 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b64e6a6747bdc701de290ae0b1e7c3706fbca582 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc": 0.355, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013819249004047296 + }, + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc_norm": 0.33916666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013672343491681819 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1fa62233b2ced0dc2c17962b9658f776f9b75e26 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc": 0.33166666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.01359683672948517 + }, + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc_norm": 0.3233333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.01350837286730022 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d79aacda271fe0ade3c173f8e82ff0dc8030de7f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc": 0.345, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013728421539454878 + }, + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc_norm": 0.3541666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013811933499570956 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..98cc7388b926fe628c84e6616eda0df80daf2ec7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc": 0.3408333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013688600793296939 + }, + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc_norm": 0.33416666666666667, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013622434813136765 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..65515620245f5751f42610dbbc464d5781e286c4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_anli_r3_justified-in-saying_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc": 0.32666666666666666, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_stderr": 0.013544340907003663 + }, + { + "task_name": "anli_r3", + "prompt_name": "justified in saying", + "acc_norm": 0.3233333333333333, + "dataset_path": "anli", + "dataset_name": null, + "subset": 3, + "acc_norm_stderr": 0.013508372867300231 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_0.json new file mode 100644 index 0000000000000000000000000000000000000000..683eda05129dcfa5698bc29313bed97610e05bf0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.2175767918088737, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.0120572620209725 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.2175767918088737, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.0120572620209725 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_1.json new file mode 100644 index 0000000000000000000000000000000000000000..64b1d8c945e360c0ae9595612252d0cb3b61eb14 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.23378839590443687, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012368225378507148 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.23378839590443687, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012368225378507148 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_2.json new file mode 100644 index 0000000000000000000000000000000000000000..423c061ef0698369ebe3fe53ae5da423209579a6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.23208191126279865, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012336718284948854 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.23208191126279865, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012336718284948854 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_3.json new file mode 100644 index 0000000000000000000000000000000000000000..e64f3bfc1e20bc9544543b0ab1838d6adab97c78 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.24146757679180889, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012506564839739429 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.24146757679180889, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012506564839739429 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_4.json new file mode 100644 index 0000000000000000000000000000000000000000..fac06e52efd26fdf0b3c382a4d9bfdb47538db08 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.24146757679180889, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012506564839739429 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.24146757679180889, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012506564839739429 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b33c9b1ef51efecb07ffd3f0c52b8005b1622be3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_heres_a_problem_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.23378839590443687, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012368225378507144 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.23378839590443687, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012368225378507144 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.json new file mode 100644 index 0000000000000000000000000000000000000000..cb37ab15fe2bb62930e8ec30ebf61b6e2aa8ff4f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.2158703071672355, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012022975360030675 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2696245733788396, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012968040686869157 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.json new file mode 100644 index 0000000000000000000000000000000000000000..4595d23a10b67a8bf57305a60ebc188d1910a487 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.2235494880546075, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012174896631202605 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.27303754266211605, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.01301933276263573 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.json new file mode 100644 index 0000000000000000000000000000000000000000..4306b92a0b4fc6f45b57734933f994af733487cb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.2167235494880546, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012040156713481189 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.26621160409556316, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012915774781523216 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ea8d4b65bb385a6e05c8d3c51820421774bf76a7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.2295221843003413, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012288926760890788 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2713310580204778, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012993807727545784 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3e635368bdc498a9938ef4fb365eb3ca1781975d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.23037542662116042, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.01230492841874761 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2713310580204778, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012993807727545784 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.json new file mode 100644 index 0000000000000000000000000000000000000000..89e02d392f62452b4e95ef1c6839ea8832ba772f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_i_am_hesitating_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.22610921501706485, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.01222420209706329 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2627986348122867, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012862523175351331 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_0.json new file mode 100644 index 0000000000000000000000000000000000000000..337f126dcfb632b1c4e52b80aad59c6ad059afd3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.22013651877133106, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.01210812488346098 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.2696245733788396, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012968040686869166 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_1.json new file mode 100644 index 0000000000000000000000000000000000000000..0af4b8a6de99e2d51329f2b6e6039fc7328f2f6e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.22866894197952217, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.01227285358254081 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.25426621160409557, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012724999945157744 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_2.json new file mode 100644 index 0000000000000000000000000000000000000000..72c3bfbc42aea161bd30ef546e4307e4c9a9a060 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.2098976109215017, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.011900548748047433 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.24914675767918087, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.01263940711192643 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_3.json new file mode 100644 index 0000000000000000000000000000000000000000..9037979f528fa23f34742b2cf9541d28b92a671c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.21331058020477817, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.011970971742326334 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.24658703071672355, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.01259572626879013 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ccdd9fe1d70558bf8c169689cbf285fd2c3acaa0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.21331058020477817, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.011970971742326334 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.25170648464163825, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012682496334042965 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_5.json new file mode 100644 index 0000000000000000000000000000000000000000..46549a6fe2203062b6b27eb05b9f5cd3a13d3118 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_multiple_choice_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.21331058020477817, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.011970971742326334 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.24658703071672355, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012595726268790132 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c394f05e47b89a366bf7960a3babeeb6ae379d4e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.22013651877133106, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012108124883460976 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.22013651877133106, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012108124883460976 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b73aa90b2f2a0fc791fc7799f9e8e2be45004366 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.2295221843003413, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012288926760890795 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.2295221843003413, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012288926760890795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.json new file mode 100644 index 0000000000000000000000000000000000000000..bde46d5c08961725eb39dbcce76c8b7de3bb9cd5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.22440273037542663, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012191404938603836 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.22440273037542663, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012191404938603836 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.json new file mode 100644 index 0000000000000000000000000000000000000000..02da04430ed2d795df397a4b016e38710fa25797 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.23720136518771331, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012430399829260846 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.23720136518771331, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012430399829260846 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b71781d589426017ce328f2e3404dcf2e0e344c6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.24573378839590443, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012581033453730106 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.24573378839590443, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012581033453730106 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.json new file mode 100644 index 0000000000000000000000000000000000000000..3fe99b2bda3fa6c881bd2890cf2e28872f563bce --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_pick_the_most_correct_option_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.22866894197952217, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012272853582540806 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.22866894197952217, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012272853582540806 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..cefc57823d5bdff7ba4a10706b46c8df01d21484 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.20648464163822525, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.011828865619002316 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.26109215017064846, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012835523909473845 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..53bcaaf8a5bea35bc5af075ae0e1617cefb61821 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2175767918088737, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012057262020972504 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.25426621160409557, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012724999945157743 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..8e5c1fdf3ea677544ec7abe0bae0d5ef16b5fed2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2098976109215017, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.011900548748047449 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.26621160409556316, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012915774781523219 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..93c86f5c1291ed0cb4284e82a5af4d6a07ec3632 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.23037542662116042, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.01230492841874761 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.26706484641638223, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012928933196496342 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8fe95acab7687ff8ae550b7d4c0713d6bba0f75d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2150170648464164, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012005717634133616 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.2525597269624573, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.01269672898020771 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b90937d64b43fd63db08c1cc86d2a7fe13c92b59 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_challenge_qa_options_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.22184300341296928, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_stderr": 0.012141659068147879 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.25853242320819114, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Challenge", + "subset": null, + "acc_norm_stderr": 0.012794553754288673 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2956f55d97d4257394b732524f4aa6de1f80c0eb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.24452861952861954, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.00881946110682261 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.24452861952861954, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00881946110682261 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_1.json new file mode 100644 index 0000000000000000000000000000000000000000..fb961059d7a232c276629ec2c0c41a3ac5937447 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.23779461279461278, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008735850753507994 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.23779461279461278, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008735850753507994 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_2.json new file mode 100644 index 0000000000000000000000000000000000000000..9eabca6f2b8a28dfe246664662348d02a118c702 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.2588383838383838, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008987501845758049 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.2588383838383838, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008987501845758049 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_3.json new file mode 100644 index 0000000000000000000000000000000000000000..057e81f09abbdc5a33fe7adc4cf228b0df9dbab8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.25841750841750843, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008982741341291298 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.25841750841750843, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008982741341291298 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b479a9cf84852293cacc4c54544ac6dae7183dea --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.25336700336700335, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008924765424529264 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.25336700336700335, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008924765424529264 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_5.json new file mode 100644 index 0000000000000000000000000000000000000000..128556531d7064c502d5f5cc9ac4f0ed3a45814a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_heres_a_problem_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc": 0.25715488215488214, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008968394768971991 + }, + { + "task_name": "arc_easy", + "prompt_name": "heres_a_problem", + "acc_norm": 0.25715488215488214, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008968394768971991 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_0.json new file mode 100644 index 0000000000000000000000000000000000000000..45e410f3f820e051c7f6cc9520148741e7134a27 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.29503367003367004, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009358110551087425 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2836700336700337, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009249781691140749 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_1.json new file mode 100644 index 0000000000000000000000000000000000000000..51a9a441237465cdd23cb10f78877433188a3b55 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.281986531986532, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009233124071053648 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.27441077441077444, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009156177122244527 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e19dab1cb122142433774b6b1078f1d864d8d923 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.27904040404040403, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009203588704032635 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2748316498316498, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009160538115254954 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_3.json new file mode 100644 index 0000000000000000000000000000000000000000..46cca0f972ce4f36b13f05a3cbb1ee58b876ed39 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.2803030303030303, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009216306864088033 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.27314814814814814, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009143032718360347 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e6962e53d13304794bf1a482d3c9239e4525d603 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.273989898989899, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009151805901544022 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.26725589225589225, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009080463246017469 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c904dfa6bbbd61e528bbd0c5669257583306da4f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_i_am_hesitating_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc": 0.2769360269360269, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009182190173795889 + }, + { + "task_name": "arc_easy", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.2680976430976431, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00908952657821369 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_0.json new file mode 100644 index 0000000000000000000000000000000000000000..4ebe45fb7b2b5733b6a5776819357dc5a3ad618b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.29124579124579125, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009322788837938871 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.2676767676767677, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00908500014709935 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_1.json new file mode 100644 index 0000000000000000000000000000000000000000..1950d08f83deacf345306f3ded7818f6d82a9dd0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.2857744107744108, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.00927038060698121 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.2807239057239057, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009220526174711353 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_2.json new file mode 100644 index 0000000000000000000000000000000000000000..38842155b1b0c27fb1171c2f68b0c4404fca9e87 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.2895622895622896, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009306838912173909 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.28619528619528617, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009274470774627732 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_3.json new file mode 100644 index 0000000000000000000000000000000000000000..37a791c65245367185e1a46ae4522a2276447e8e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.27735690235690236, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009186490105111902 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.2962962962962963, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009369711585684304 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8cd344abbc29e955eff29691b1a84f364283274d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.2781986531986532, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009195059601583901 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.2845117845117845, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00925805092561882 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_5.json new file mode 100644 index 0000000000000000000000000000000000000000..1732fb010ba571916ef47de3f14a5a7e32c7f9b9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_multiple_choice_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc": 0.2735690235690236, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009147424438490745 + }, + { + "task_name": "arc_easy", + "prompt_name": "multiple_choice", + "acc_norm": 0.2878787878787879, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009290733161670155 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.json new file mode 100644 index 0000000000000000000000000000000000000000..9243820a1cca7bd3c91ac5088897ba33cf50428f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.24873737373737373, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008870224411653796 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.24873737373737373, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008870224411653796 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f2c028dd0eb88f669c357af30021280a6694bf6c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.2398989898989899, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008762298774190588 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.2398989898989899, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008762298774190588 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.json new file mode 100644 index 0000000000000000000000000000000000000000..894ec9c5980cfab171c9679fd525e6295dcf4116 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.2596801346801347, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008996990428562215 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.2596801346801347, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008996990428562215 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7f6c3a147f95efbc7a6fc0ac0619a4b6534f7a65 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.2537878787878788, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.00892965706580829 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.2537878787878788, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00892965706580829 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bae2c7b0e98da13e7fb2f26d7422d2a3992b7485 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.2542087542087542, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008934537681141544 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.2542087542087542, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008934537681141544 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a1619a5d1e34e7368255e8744630c1373f6df08c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_pick_the_most_correct_option_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc": 0.25925925925925924, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.008992251535805518 + }, + { + "task_name": "arc_easy", + "prompt_name": "pick_the_most_correct_option", + "acc_norm": 0.25925925925925924, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.008992251535805518 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..92d47f74dc7ac681fbfb93c0d058d6f7554c4aab --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.3005050505050505, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009407763090599318 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.2760942760942761, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00917355987383526 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d715dd9d9f579f764279bf21c1205beb6d025634 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.29503367003367004, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009358110551087425 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.28114478114478114, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009224735470287005 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..bcb80967470837097ea3a20838b081f8b3ef38c9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2908249158249158, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009318815921176653 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.27441077441077444, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009156177122244528 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..20abbee19c3f820c39f67727f50fb3e28bbe4f0a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2824074074074074, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009237303403479332 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.2756734006734007, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009169229476542563 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..9217f2be5c9e12d6b2e66a2c2288838b09172d33 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2781986531986532, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.0091950596015839 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.2727272727272727, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.00913863072636423 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..1dc5a18c5d3ce8fc3629a685ac113afd81337629 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_arc_easy_qa_options_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc": 0.2824074074074074, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_stderr": 0.009237303403479334 + }, + { + "task_name": "arc_easy", + "prompt_name": "qa_options", + "acc_norm": 0.27146464646464646, + "dataset_path": "ai2_arc", + "dataset_name": "ARC-Easy", + "subset": null, + "acc_norm_stderr": 0.009125362970360623 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..5650460e707b1328e272ce63f9219a4786cd134a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc": 0.48933333333333334, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009128153252511649 + }, + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc_norm": 0.6233333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00884811049411477 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c04fb92c04df018af591bcb4e8c12a406d93097b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc": 0.5403333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009100476927108948 + }, + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc_norm": 0.5463333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00909094544975723 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..825f52f7b3a765c53b32d1339700d62c797b192a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc": 0.5376666666666666, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.00910428672401049 + }, + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc_norm": 0.5733333333333334, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009031496556538196 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..283c66988f45409ee5ecf3f7402b5b323d02a120 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc": 0.561, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009062029213030572 + }, + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc_norm": 0.5776666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009019409415904176 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..cec9d94c051ccd26e210704c76eacd5a7f328635 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc": 0.5606666666666666, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009062775319073724 + }, + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc_norm": 0.575, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009026931658379627 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..dbb3c11855d77873fd0338ec5a677aaf4842ba1f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_GPT-3-Style_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc": 0.564, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009055127374988182 + }, + { + "task_name": "boolq", + "prompt_name": "GPT-3 Style", + "acc_norm": 0.581, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009009627690997004 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_0.json new file mode 100644 index 0000000000000000000000000000000000000000..473258face5630defa038ed4c2cface95d5c288b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc": 0.6196666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008864883436857793 + }, + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc_norm": 0.485, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009126121594912155 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_1.json new file mode 100644 index 0000000000000000000000000000000000000000..4e56e9715d62d91b48b15e2086ec48a4ae189647 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc": 0.5406666666666666, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009099982269204863 + }, + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc_norm": 0.5403333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009100476927108948 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_2.json new file mode 100644 index 0000000000000000000000000000000000000000..30a6b607be091adfd50be2ae6f0e0db668a48453 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc": 0.5213333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009121916798841863 + }, + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc_norm": 0.5053333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009129711700290994 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_3.json new file mode 100644 index 0000000000000000000000000000000000000000..297201be721f2560f2453cd502de09625330a824 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009084465266030921 + }, + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc_norm": 0.545, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009093178503605498 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_4.json new file mode 100644 index 0000000000000000000000000000000000000000..560e289c60c48c2875cfcd1abdfad1354b75b63f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc": 0.5443333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.00909427038138736 + }, + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc_norm": 0.536, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009106534814375938 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_5.json new file mode 100644 index 0000000000000000000000000000000000000000..60f4c1e3656058764189f19dcbdd4acf408a5036 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_after_reading_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc": 0.5556666666666666, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.00907346956924853 + }, + { + "task_name": "boolq", + "prompt_name": "after_reading", + "acc_norm": 0.5493333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009085680525105019 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_0.json new file mode 100644 index 0000000000000000000000000000000000000000..f4f3e12afc901c9f801854cb8a5af4efae6b8d4b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc": 0.6203333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008861873799148993 + }, + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc_norm": 0.38166666666666665, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.008870849530787627 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_1.json new file mode 100644 index 0000000000000000000000000000000000000000..a4da0095394a545af197a41ff22006bd3379dfca --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc": 0.5406666666666666, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009099982269204863 + }, + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc_norm": 0.541, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009099483512819305 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_2.json new file mode 100644 index 0000000000000000000000000000000000000000..3267454eea993087d033526d54a67da3da3c11d1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc": 0.56, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009064255084676055 + }, + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc_norm": 0.5536666666666666, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00907748661345029 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a919484403aaf750ad0c7ea6c57f9e45fcf1a38d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc": 0.5726666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009033293159951222 + }, + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc_norm": 0.564, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009055127374988184 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_4.json new file mode 100644 index 0000000000000000000000000000000000000000..386762c069b491ab37e1d04b32981a2442e710c0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc": 0.581, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009009627690997004 + }, + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc_norm": 0.5686666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00904372116961954 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_5.json new file mode 100644 index 0000000000000000000000000000000000000000..ebf89d2e87a7114c24c99abeb4ac65106cb8b4af --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_exercise_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc": 0.5846666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008998379972670818 + }, + { + "task_name": "boolq", + "prompt_name": "exercise", + "acc_norm": 0.579, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009015547313638383 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..ad5e2021202a257c5515c7b1bc41b38f79181a80 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc": 0.5126666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.00912730086383017 + }, + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc_norm": 0.3893333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00890378508047089 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..007f5169233a252bd201507decb5163a695ce509 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc": 0.5403333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009100476927108948 + }, + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc_norm": 0.5403333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009100476927108948 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..91bb63736e0314d449ca2b38403d947de2ef2360 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc": 0.556, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009072785596468857 + }, + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc_norm": 0.542, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009097962646004978 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..70b701e8767cce8685316917f67c1c4d43662300 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc": 0.5573333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009070008341418438 + }, + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc_norm": 0.5473333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.009089227499483243 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b187bcc6e534630d6a4a76519b4bad25b37b9605 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc": 0.5676666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.009046234144187919 + }, + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc_norm": 0.5533333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00907814166393873 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..eb8bff0544a1b8118e0eaae4f51cc6f1bea97bd3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_valid_binary_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc": 0.5763333333333334, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.0090232041691723 + }, + { + "task_name": "boolq", + "prompt_name": "valid_binary", + "acc_norm": 0.5696666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00904117061597785 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a44179cff27bf1f000385c221268dbf1e9aee7ae --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc": 0.6236666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008846558976258922 + }, + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc_norm": 0.6236666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.008846558976258922 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b5ad16c289597879063e99b0b726022ceab4fefa --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc": 0.6153333333333333, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.00888401463187693 + }, + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc_norm": 0.624, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.008845002997512754 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_2.json new file mode 100644 index 0000000000000000000000000000000000000000..978b9545c91ce34c3bea49ba6da8090af381067b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc": 0.6126666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008895417372116209 + }, + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc_norm": 0.622, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00885427200344005 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_3.json new file mode 100644 index 0000000000000000000000000000000000000000..e82f3cc92dc84938e714adddfdbfc4d4993ddaa9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc": 0.613, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008894007408882734 + }, + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc_norm": 0.6156666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.008882569490543052 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ebe422da87d629d5fa8877d18c90ee63a63610fa --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc": 0.6226666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.00885120015653439 + }, + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc_norm": 0.624, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.00884500299751275 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_5.json new file mode 100644 index 0000000000000000000000000000000000000000..ce485e2b23a24957a64df6ee40233f222c7bf451 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_boolq_yes_no_question_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc": 0.6216666666666667, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_stderr": 0.008855801251873017 + }, + { + "task_name": "boolq", + "prompt_name": "yes_no_question", + "acc_norm": 0.624, + "dataset_path": "super_glue", + "dataset_name": "boolq", + "subset": null, + "acc_norm_stderr": 0.008845002997512754 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..5efe4141dfd2ffbe8efd19a22bf028748745874a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_0.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "acc": 0.32142857142857145, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06297362289056341 + }, + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "f1": 0.16666666666666666, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..a3f03d07eda5127124eda7c35a978a32788d1ae4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_1.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "acc": 0.35714285714285715, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06460957383809221 + }, + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "f1": 0.2247097844112769, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f80a533fab77edcf7f3ad600fb441c98e96815a5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_2.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0663363415035954 + }, + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "f1": 0.24232804232804236, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a552da01769e2bff4a1980eb8029b46977257a13 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_3.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0658538889806635 + }, + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "f1": 0.2075, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b1fb836228b784fa984d06c27827e3fbd5b93f7c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_4.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "acc": 0.375, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06527912098338669 + }, + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "f1": 0.18421052631578946, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..310ae643bd8c3a9e765616041c5e9fdb837b57bc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_GPT-3-style_5.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0658538889806635 + }, + { + "task_name": "cb", + "prompt_name": "GPT-3 style", + "f1": 0.19047619047619047, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..43e155b9dceb22c292b924ccd2f4b8fb1592d0c4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_0.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06633634150359538 + }, + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "f1": 0.1940928270042194, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..3584c7cfb43721c445be4ee923e571e763092ab8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_1.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0658538889806635 + }, + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "f1": 0.2842025699168556, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..5836f3f08d31c91b5b0b5f2f944833304bf1f64a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_2.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "acc": 0.42857142857142855, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06672848092813058 + }, + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "f1": 0.29715109989181393, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..dc02d27d61ad5e57c08e85c463ed486e6e3896dd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_3.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "acc": 0.44642857142857145, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.067031892279424 + }, + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "f1": 0.31340255400405775, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..cab1a2a41671dd15dbef475d044a27070c9272f4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_4.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06585388898066351 + }, + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "f1": 0.2647907647907648, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..7a0ceaa4f31858be01faafa7897937a0b9c22991 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_MNLI-crowdsource_5.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "acc": 0.35714285714285715, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0646095738380922 + }, + { + "task_name": "cb", + "prompt_name": "MNLI crowdsource", + "f1": 0.24618343550907562, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e3007f6959f5cfd81db4073dce5d4e7621b58b07 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_0.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "can we infer", + "acc": 0.42857142857142855, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06672848092813058 + }, + { + "task_name": "cb", + "prompt_name": "can we infer", + "f1": 0.2791044776119403, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_1.json new file mode 100644 index 0000000000000000000000000000000000000000..8ee9ffacff3543d38d12892662740cbb36f15f3d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_1.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "can we infer", + "acc": 0.4642857142857143, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0672477765493766 + }, + { + "task_name": "cb", + "prompt_name": "can we infer", + "f1": 0.3227969348659004, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_2.json new file mode 100644 index 0000000000000000000000000000000000000000..4828003dc16e51e15f93343c8a1ca7354b233295 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_2.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "can we infer", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06633634150359541 + }, + { + "task_name": "cb", + "prompt_name": "can we infer", + "f1": 0.27519379844961245, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8b682d8565acb7f5ac9be56b8cc8244ce50cb250 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_3.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "can we infer", + "acc": 0.4642857142857143, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0672477765493766 + }, + { + "task_name": "cb", + "prompt_name": "can we infer", + "f1": 0.311531007751938, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_4.json new file mode 100644 index 0000000000000000000000000000000000000000..6ef18e9922d33f28ae334b8ebb75bdeecafae244 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_4.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "can we infer", + "acc": 0.42857142857142855, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06672848092813058 + }, + { + "task_name": "cb", + "prompt_name": "can we infer", + "f1": 0.2905242905242906, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_5.json new file mode 100644 index 0000000000000000000000000000000000000000..60c4c355aebec36843090e3e093060d57910499c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_can-we-infer_5.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "can we infer", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0663363415035954 + }, + { + "task_name": "cb", + "prompt_name": "can we infer", + "f1": 0.2798088410991637, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.json new file mode 100644 index 0000000000000000000000000000000000000000..537da6fb4d92b4c0481f2afd355ebb9c060cc884 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_0.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0658538889806635 + }, + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "f1": 0.3166447079490558, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.json new file mode 100644 index 0000000000000000000000000000000000000000..baa09f7b8d3e9119bff84c4301a162fbefe6a1a6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_1.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0658538889806635 + }, + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "f1": 0.2842025699168556, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0b1896cf228f00b04053ebe91cb5e6c3250b0df3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_2.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.44642857142857145, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06703189227942398 + }, + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "f1": 0.29843652282676675, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.json new file mode 100644 index 0000000000000000000000000000000000000000..91e581b311a2831b6824187d6f8db98afd08d3dd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_3.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06633634150359541 + }, + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "f1": 0.23085585585585586, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.json new file mode 100644 index 0000000000000000000000000000000000000000..8c7f48a9f5198bc0d5ece8a8845f90b80620a66a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_4.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.5178571428571429, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06737697508644647 + }, + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "f1": 0.2908378541289934, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2091513af2d1a9ac0693f398328b29e77162f302 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_guaranteed-possible-impossible_5.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "acc": 0.5, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06741998624632421 + }, + { + "task_name": "cb", + "prompt_name": "guaranteed/possible/impossible", + "f1": 0.2660493827160494, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_0.json new file mode 100644 index 0000000000000000000000000000000000000000..3f25d39da680d6cab24503dd5e8948c6d194c11d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_0.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "justified in saying", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06633634150359538 + }, + { + "task_name": "cb", + "prompt_name": "justified in saying", + "f1": 0.2144878324844369, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_1.json new file mode 100644 index 0000000000000000000000000000000000000000..70d10a3f6afc716814864c72ef9512f2d798d58a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_1.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "justified in saying", + "acc": 0.4642857142857143, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0672477765493766 + }, + { + "task_name": "cb", + "prompt_name": "justified in saying", + "f1": 0.3227969348659004, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_2.json new file mode 100644 index 0000000000000000000000000000000000000000..73943d105536a231d03d78dcd973da45b9f95a8a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_2.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "justified in saying", + "acc": 0.4107142857142857, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06633634150359541 + }, + { + "task_name": "cb", + "prompt_name": "justified in saying", + "f1": 0.27519379844961245, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_3.json new file mode 100644 index 0000000000000000000000000000000000000000..39a3fb3dabb587a9245cf9458e68c01ad15aa800 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_3.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "justified in saying", + "acc": 0.44642857142857145, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.067031892279424 + }, + { + "task_name": "cb", + "prompt_name": "justified in saying", + "f1": 0.29572649572649573, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ffb118a8a42df31022cff02f2340c86a9f3d06b6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_4.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "justified in saying", + "acc": 0.42857142857142855, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.06672848092813058 + }, + { + "task_name": "cb", + "prompt_name": "justified in saying", + "f1": 0.2854700854700854, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_5.json new file mode 100644 index 0000000000000000000000000000000000000000..422d5d64aa3911cc3fcf4f39bc9497a42052746f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_cb_justified-in-saying_5.json @@ -0,0 +1,33 @@ +{ + "results": [ + { + "task_name": "cb", + "prompt_name": "justified in saying", + "acc": 0.39285714285714285, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null, + "acc_stderr": 0.0658538889806635 + }, + { + "task_name": "cb", + "prompt_name": "justified in saying", + "f1": 0.2524875621890547, + "dataset_path": "super_glue", + "dataset_name": "cb", + "subset": null + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_0.json new file mode 100644 index 0000000000000000000000000000000000000000..01533dfaf3eedf57b9229df9ffc30d2a348827e8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "best_option", + "acc": 0.58, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.049604496374885836 + }, + { + "task_name": "copa", + "prompt_name": "best_option", + "acc_norm": 0.5, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050251890762960605 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f9538ed9e58c4e5049456a32f97374c92e040e23 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "best_option", + "acc": 0.53, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05016135580465919 + }, + { + "task_name": "copa", + "prompt_name": "best_option", + "acc_norm": 0.47, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05016135580465919 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f02f48b22d3d16bda51629f3071e41af17d8fb4b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "best_option", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05 + }, + { + "task_name": "copa", + "prompt_name": "best_option", + "acc_norm": 0.49, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956912 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d5a36f0ab63ea6bac084f2c68925dd05e6421703 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "best_option", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05 + }, + { + "task_name": "copa", + "prompt_name": "best_option", + "acc_norm": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_4.json new file mode 100644 index 0000000000000000000000000000000000000000..d709a19cbe071140797941c32f32c99063ad1ed5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "best_option", + "acc": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05024183937956911 + }, + { + "task_name": "copa", + "prompt_name": "best_option", + "acc_norm": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956911 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_5.json new file mode 100644 index 0000000000000000000000000000000000000000..763059301a0870e3cbef000e7cf7c22d251bd7d6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_best_option_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "best_option", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05 + }, + { + "task_name": "copa", + "prompt_name": "best_option", + "acc_norm": 0.59, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.04943110704237101 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_0.json new file mode 100644 index 0000000000000000000000000000000000000000..5def71c6f12d0345a1bd0af1d576e73aa6b213d6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc": 0.59, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.049431107042371025 + }, + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc_norm": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956912 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_1.json new file mode 100644 index 0000000000000000000000000000000000000000..85479ee0c78dab0102bab969259fce23faf33474 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc": 0.54, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05009082659620332 + }, + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc_norm": 0.46, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05009082659620332 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1b97c17e1f85938e7218cd9616113accf86f227f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc": 0.56, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.04988876515698589 + }, + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc_norm": 0.48, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_3.json new file mode 100644 index 0000000000000000000000000000000000000000..fb8234c3ceb2d666333a0149a30d1cb7d1169816 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc": 0.54, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05009082659620333 + }, + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc_norm": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_4.json new file mode 100644 index 0000000000000000000000000000000000000000..2a56967376892a0c5086f72b1f98b9ed592c3f92 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05 + }, + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc_norm": 0.54, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05009082659620333 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_5.json new file mode 100644 index 0000000000000000000000000000000000000000..0bfff7f6d1074ef177f5ebf72e92434c293b47b6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_cause_effect_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc": 0.54, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05009082659620333 + }, + { + "task_name": "copa", + "prompt_name": "cause_effect", + "acc_norm": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_0.json new file mode 100644 index 0000000000000000000000000000000000000000..885730628febb14f714fa98de3ec09e175a7635c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "choose", + "acc": 0.58, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.049604496374885836 + }, + { + "task_name": "copa", + "prompt_name": "choose", + "acc_norm": 0.54, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05009082659620332 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_1.json new file mode 100644 index 0000000000000000000000000000000000000000..574111f40843e8de0da854efabb4e81d7611eb5d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "choose", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05 + }, + { + "task_name": "copa", + "prompt_name": "choose", + "acc_norm": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_2.json new file mode 100644 index 0000000000000000000000000000000000000000..5a14185579b9527e51c9f55c773414787dcf1366 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "choose", + "acc": 0.55, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05 + }, + { + "task_name": "copa", + "prompt_name": "choose", + "acc_norm": 0.49, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956912 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_3.json new file mode 100644 index 0000000000000000000000000000000000000000..f75fd09a6f9ad3905919aff4952c21b67eb1875d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "choose", + "acc": 0.53, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05016135580465919 + }, + { + "task_name": "copa", + "prompt_name": "choose", + "acc_norm": 0.5, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050251890762960605 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_4.json new file mode 100644 index 0000000000000000000000000000000000000000..ea9a2b5a6698d6450f7c796a092754c6167c7171 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "choose", + "acc": 0.54, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05009082659620333 + }, + { + "task_name": "copa", + "prompt_name": "choose", + "acc_norm": 0.49, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956912 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_5.json new file mode 100644 index 0000000000000000000000000000000000000000..dbdc6d30f3563f5e900cc5ca6d6471a7704996a0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_choose_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "choose", + "acc": 0.53, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050161355804659205 + }, + { + "task_name": "copa", + "prompt_name": "choose", + "acc_norm": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d997448e77c0e8e7bc8f31efa42626113159ac58 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc": 0.56, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.049888765156985884 + }, + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956912 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b04475aeadddc5ff96128afff2a456d7267d62d3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc": 0.48, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050211673156867795 + }, + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.45, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.049999999999999996 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_2.json new file mode 100644 index 0000000000000000000000000000000000000000..b12c19e4e965b72bf1b0d64300af912426732a91 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050211673156867795 + }, + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_3.json new file mode 100644 index 0000000000000000000000000000000000000000..cc8c46875500f0708d1bed5abb33ebb94a5dcf9d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc": 0.49, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05024183937956912 + }, + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956911 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b4fa62d652d63d00a6c59e4c2438e9d68d0985e4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc": 0.47, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05016135580465919 + }, + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.5, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050251890762960605 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_5.json new file mode 100644 index 0000000000000000000000000000000000000000..30a7ab93a2bb9ee8625c722c84725cdf951cbf2f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_i_am_hesitating_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc": 0.5, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050251890762960605 + }, + { + "task_name": "copa", + "prompt_name": "i_am_hesitating", + "acc_norm": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956911 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_0.json new file mode 100644 index 0000000000000000000000000000000000000000..f50197cba30600e65dd158c1426d5154bdae9c8f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc": 0.56, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.049888765156985884 + }, + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc_norm": 0.5, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050251890762960605 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_1.json new file mode 100644 index 0000000000000000000000000000000000000000..98a0742a44d1da9a892fd592042f2601b0dfaabc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050211673156867795 + }, + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc_norm": 0.46, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05009082659620332 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6449f1dfe66087d8e21a8f2c106acc47a8fb5809 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc": 0.53, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050161355804659205 + }, + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc_norm": 0.48, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_3.json new file mode 100644 index 0000000000000000000000000000000000000000..046dad6ca5f2e6b3ba8b78c2bd9d4cde3f87826b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc": 0.52, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.050211673156867795 + }, + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc_norm": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.05024183937956911 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b684982cd801c7139fc9a4b06d1fe81068d1da1d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05024183937956911 + }, + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc_norm": 0.48, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_5.json new file mode 100644 index 0000000000000000000000000000000000000000..1148b5e0b01ab0a5e5a59034dea5fc91bbc22d10 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_copa_plausible_alternatives_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc": 0.51, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_stderr": 0.05024183937956911 + }, + { + "task_name": "copa", + "prompt_name": "plausible_alternatives", + "acc_norm": 0.48, + "dataset_path": "super_glue", + "dataset_name": "copa", + "subset": null, + "acc_norm_stderr": 0.050211673156867795 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.json new file mode 100644 index 0000000000000000000000000000000000000000..df781e3ea572b1a01231aa2962020597603c08c3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "bleu": 1.4085336184354111, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.05741951405804131 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_precision": 0.13228526132614984, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0020013074393031836 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_recall": 0.2369325887389989, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0027790980608073646 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_fmeasure": 0.16506378620343637, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0022294407692459474 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_precision": 0.034003030527238576, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0010025662026581091 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_recall": 0.056957962707056595, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016005937753295783 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_fmeasure": 0.0413168613300981, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0011779113504419888 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_precision": 0.11307449761220935, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0012999325612706172 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_recall": 0.208842612528325, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0020062255755377858 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_fmeasure": 0.14268631130584333, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0014826828522232203 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_precision": 0.10960115777847065, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.001579915881101131 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_recall": 0.19748155077377938, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022590044053826777 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_fmeasure": 0.13688623513784934, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0017661120751764666 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.json new file mode 100644 index 0000000000000000000000000000000000000000..d8b86e8bd3f232f1748b3bf45924122412f48c9b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "bleu": 4.729286166275417, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.09128304389641625 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_precision": 0.3408358446419251, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0034116541291492057 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_recall": 0.2783365471883401, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002737152709268981 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_fmeasure": 0.2892038317215652, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0025869454710142777 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_precision": 0.11786217798858512, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0020524631363241412 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_recall": 0.09241456760956686, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0015313690129086298 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_fmeasure": 0.09705173957954942, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015453194099685405 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_precision": 0.25216134633862136, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0027436356295732754 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_recall": 0.20399063384073168, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.002098237813401181 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_fmeasure": 0.21222627239556746, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0019998631000071967 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_precision": 0.28273246045224193, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0030427081908894252 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_recall": 0.22924073727175148, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0023626083063246254 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_fmeasure": 0.23867678360949154, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0022704869608702 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a3d5493c12a9a9cf342e87b45354ad41b418c24c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "bleu": 6.325316845200212, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.09823383956529014 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_precision": 0.3908301753738232, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031422044941371253 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_recall": 0.32494169596300476, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024924666531749825 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_fmeasure": 0.33385083240638835, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0022057300734858753 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_precision": 0.1514609363136513, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022477501689905873 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_recall": 0.12052118677866239, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016199084429215386 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_fmeasure": 0.12480576931000954, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001582754162108835 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_precision": 0.293562283125087, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002707140102409516 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_recall": 0.24127140452116988, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019870656915090814 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_fmeasure": 0.2482760515483937, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017935997104643916 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_precision": 0.32736403463849806, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002914041154580964 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_recall": 0.2701473844458722, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022228285101149096 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_fmeasure": 0.27814692011572395, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.00202476127925843 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.json new file mode 100644 index 0000000000000000000000000000000000000000..14263a77d9ad78b1bc5b4831dd57fd2e9b6c879a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "bleu": 7.093242387648388, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1779108642695036 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_precision": 0.4033568597868611, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0030439856617461825 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_recall": 0.3393497221509125, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024495138617378286 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_fmeasure": 0.3468468278255215, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002126607440022899 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_precision": 0.1603885963824591, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002211321437110491 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_recall": 0.1297128662599877, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016715601470477192 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_fmeasure": 0.13345925813528606, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016050391064121614 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_precision": 0.30327882804864414, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026682405889953253 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_recall": 0.2518780545862424, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019409034909989161 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_fmeasure": 0.25781869559651055, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017250105332014863 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_precision": 0.33832600518727873, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002866030451437672 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_recall": 0.2824307369414572, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0021987427091062425 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_fmeasure": 0.28922616836791826, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019740744474346238 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.json new file mode 100644 index 0000000000000000000000000000000000000000..735ecc679c2038699abb4b234734a3cfe67f507a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "bleu": 7.441380932329685, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.13415864466690663 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_precision": 0.40930270509361055, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003082794337886431 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_recall": 0.34406073111724306, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024467984658659457 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_fmeasure": 0.3513421927671594, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021279258327609294 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_precision": 0.16770678005567702, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022910300764590334 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_recall": 0.1356936401482478, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017118286189666942 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_fmeasure": 0.139368667490815, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016374065418968793 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_precision": 0.30955103142076024, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026954850190455738 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_recall": 0.25780563970283943, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019854199620409053 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_fmeasure": 0.2632971395760134, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.001761093443585716 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_precision": 0.34462560843141665, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0028969602572112584 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_recall": 0.2875465717034684, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002202341197956502 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_fmeasure": 0.294208873461138, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001978637458277599 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2d701b41cd9a838441925cfa51a536f5704636ea --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_coherent_text_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "bleu": 7.5737114766827744, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.16631977129206255 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_precision": 0.41687585365688856, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031195723945421903 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_recall": 0.3459752611920822, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002424143041978818 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge1_fmeasure": 0.3550742864577696, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021015187822019713 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_precision": 0.1733553595449332, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0023061322348589372 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_recall": 0.13907964535601638, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001719596537412042 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rouge2_fmeasure": 0.1433273164318412, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016448122877788167 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_precision": 0.3185451706746064, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002764987760129163 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_recall": 0.2618919651726129, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001983008971819947 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeL_fmeasure": 0.2689262922478298, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017684452634382998 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_precision": 0.353237732771995, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029473597771023205 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_recall": 0.2916978400324908, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022123740894828313 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "coherent_text", + "rougeLsum_fmeasure": 0.29967975079613524, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001985017926935537 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.json new file mode 100644 index 0000000000000000000000000000000000000000..caba65fea3289aa59229edb6524971d796592e0a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "bleu": 2.703242330052237, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.053740475370982206 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_precision": 0.2661363538943579, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.002367715966031621 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_recall": 0.43300283554036917, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.004390407342450644 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_fmeasure": 0.3195200501284644, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0029128906590861338 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_precision": 0.11474242753676482, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0010312600650423582 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_recall": 0.1866895759452563, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.002052535203353899 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_fmeasure": 0.13691922129643072, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0012702596895246712 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_precision": 0.17937558305738294, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0013720245995724903 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_recall": 0.28616889513557914, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0026317983935095325 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_fmeasure": 0.21271540347370638, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0016500637313875428 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_precision": 0.21948638044662674, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0018609668228193143 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_recall": 0.3521509345321294, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.00340514324563439 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_fmeasure": 0.26161394912968283, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0022526565471884855 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.json new file mode 100644 index 0000000000000000000000000000000000000000..637249345c872bc4bd5fbdb400bf7693c15d9fd2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "bleu": 4.577776049140263, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.09034061701953547 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_precision": 0.34100807827295837, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003184063014013613 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_recall": 0.27941656720882674, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0026026095744065953 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_fmeasure": 0.29090627143470194, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0024330971957175203 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_precision": 0.11175648476464418, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0019681372052978165 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_recall": 0.08832198666750592, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0014790311360637835 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_fmeasure": 0.09291021571347792, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015027135995425269 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_precision": 0.25053169214166077, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0025671894408817466 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_recall": 0.20342961186323133, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001994180509072628 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_fmeasure": 0.21213952158968352, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018872143094313097 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_precision": 0.28172377076654426, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002852857226376121 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_recall": 0.22946240670401793, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002255076858855054 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_fmeasure": 0.2393285330033846, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.00214964727816577 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.json new file mode 100644 index 0000000000000000000000000000000000000000..66a55fc9e89cbc666b3c63ef14135b9e2c35f91b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "bleu": 5.98205212345435, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1280571718069931 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_precision": 0.3823214924637971, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003024709228079845 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_recall": 0.3204650885914036, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002430593485338909 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_fmeasure": 0.32884340089308617, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002135142045723192 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_precision": 0.14073383940982426, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002136791451462909 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_recall": 0.11362566019027333, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001592486151354374 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_fmeasure": 0.11731827518171299, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015444189662990626 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_precision": 0.2851163980403521, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002571830567593308 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_recall": 0.2366396569421376, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019279427376296453 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_fmeasure": 0.24308318109830301, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.001718910616546924 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_precision": 0.31962238317070146, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002803107271378859 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_recall": 0.26621396952055804, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002177094542934803 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_fmeasure": 0.2736078163019124, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001965703958545944 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d7a62b0126c123f9804080aec6b4c67f6ed4eece --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "bleu": 6.863369305798137, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.15945748355314382 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_precision": 0.39244673058197366, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.00291042027182271 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_recall": 0.3356108550535503, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002419884948866489 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_fmeasure": 0.342206180898298, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021010446350658595 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_precision": 0.149747180591347, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002068565282156403 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_recall": 0.12431399945617358, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016576108529010333 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_fmeasure": 0.12734114879849334, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001589185479506862 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_precision": 0.2929476916339765, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.00249955074163189 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_recall": 0.24778818042905212, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019126314450433883 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_fmeasure": 0.25304733592238204, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017029355919681117 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_precision": 0.32865423091372126, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0027286585155264402 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_recall": 0.2790170412547052, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0021770844165001626 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_fmeasure": 0.2851145615546105, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019583190063539803 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.json new file mode 100644 index 0000000000000000000000000000000000000000..0f13fa4ff59232978f0b42635f87c18967ba1f1a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "bleu": 7.213329948258112, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1504445078411636 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_precision": 0.39870625613730687, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0030059139760784137 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_recall": 0.3401793704440513, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.00244816453017379 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_fmeasure": 0.34597281761424564, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021117138542066263 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_precision": 0.15639401362724684, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002182860663855212 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_recall": 0.12970046691236706, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001719867215235167 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_fmeasure": 0.1322742849122928, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016280655196310467 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_precision": 0.30042871354521805, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002604676027141301 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_recall": 0.2538632272987309, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019749848838672476 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_fmeasure": 0.25839347897511217, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.001739652960879094 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_precision": 0.33569946464927397, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002827255616797676 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_recall": 0.2846056877350737, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002227786950064511 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_fmeasure": 0.2899260055449036, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019853018337260124 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.json new file mode 100644 index 0000000000000000000000000000000000000000..85a28eec1dc47e63c55da9f98207716ae3546fd3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_create_text_for_me_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "bleu": 7.496072350547459, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.13118615529748254 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_precision": 0.4079186719686208, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0030636128374210455 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_recall": 0.34551384483174236, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024411037115400777 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge1_fmeasure": 0.3526218995116698, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021169320380915397 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_precision": 0.1651169143111655, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022498261971629634 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_recall": 0.13570208053691146, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017306096236515535 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rouge2_fmeasure": 0.13899954079181534, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016519779895088726 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_precision": 0.3103180907026251, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026794184035727514 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_recall": 0.260674271635608, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019926530246205786 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeL_fmeasure": 0.26611116257409023, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017655608447914495 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_precision": 0.34494793963685744, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002867601551740783 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_recall": 0.290738713102737, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022139980383301975 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "create_text_for_me", + "rougeLsum_fmeasure": 0.29700738879576205, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019763199856062843 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a0856358e7e8b8b5c6cc3d1aa1b4f587b31872c2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "bleu": 3.33689116446375, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.061087011177673324 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_precision": 0.16350018472386488, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0009748274524219786 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_recall": 0.15345481937904124, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0013096963261815264 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_fmeasure": 0.1544874561171709, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0010331568296333966 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_precision": 0.10930581072628082, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0009544493807060682 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_recall": 0.10394007426189322, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0011356818972608751 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_fmeasure": 0.10374767270154109, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0009552767021848785 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_precision": 0.16350018472386488, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0009748274524219786 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_recall": 0.15345481937904124, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0013096963261815264 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_fmeasure": 0.1544874561171709, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0010331568296333966 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_precision": 0.16126223153775923, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0009358067078434506 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_recall": 0.15130017670533033, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0012746322385110529 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_fmeasure": 0.15232644862442798, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.000994235301055403 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.json new file mode 100644 index 0000000000000000000000000000000000000000..22ddf44b519917378e9dc941ab2a2d0d392275e8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "bleu": 4.231103023669522, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.06401228873780763 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_precision": 0.22876696491722354, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.002309289082178887 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_recall": 0.22418518523376774, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024608018120844447 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_fmeasure": 0.21822213931750256, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002101989165296421 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_precision": 0.11900463798533546, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0013220328662893331 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_recall": 0.11426547711399747, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0013755970980597794 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_fmeasure": 0.11246784846792322, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0011969645761367486 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_precision": 0.19721866991989792, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.001448486033755209 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_recall": 0.19219429418598927, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001702222043237259 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_fmeasure": 0.18786846421672448, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.001330092385386827 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_precision": 0.2036594715170169, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0017870596309090383 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_recall": 0.19919852385897865, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002011582797896158 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_fmeasure": 0.19423470819963112, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001652146284622351 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.json new file mode 100644 index 0000000000000000000000000000000000000000..e9ede72889c995ed1a303a2943dad2f0cf914c8c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "bleu": 5.525451650396909, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1444467494539742 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_precision": 0.2834490220270683, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0030414084396847606 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_recall": 0.2715933334719839, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002848612162614692 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_fmeasure": 0.26534001970520577, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0025743732024496244 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_precision": 0.13405990343107269, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0017363915410273162 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_recall": 0.12632320690490031, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001580690379939971 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_fmeasure": 0.12416901504237551, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0014418832805010986 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_precision": 0.22739524397837393, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002045754856820925 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_recall": 0.21790717317346972, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001977682176352203 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_fmeasure": 0.21281653093345984, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0016678452099069705 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_precision": 0.24440894566677487, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0025218643599198604 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_recall": 0.23358308890323742, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0023681355345237325 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_fmeasure": 0.2284401060917875, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0021061890580456274 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.json new file mode 100644 index 0000000000000000000000000000000000000000..55444cdf7a47f5854ccdb767202167ea62787c89 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "bleu": 6.8137963757639595, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.20255562203924876 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_precision": 0.3270546311530774, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0033260484118045196 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_recall": 0.30290304692810277, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0029793997242539795 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_fmeasure": 0.29832265261949864, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002682363598114479 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_precision": 0.146059799869631, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0019394392606377293 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_recall": 0.13509651368601627, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017660311848326784 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_fmeasure": 0.1327243773594466, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016010342153913112 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_precision": 0.25289429854529516, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0023232203307966158 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_recall": 0.23497554580132518, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.002126463940220678 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_fmeasure": 0.23091319790847228, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.001809456729054163 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_precision": 0.2773139281135476, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002808432208536525 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_recall": 0.2565055228473518, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0025015169643640652 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_fmeasure": 0.2526729166449464, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0022317763780196186 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.json new file mode 100644 index 0000000000000000000000000000000000000000..46a82b4d6d5c23dfc51721bd1c01cd857366387f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "bleu": 7.341198614648136, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.17045073548615564 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_precision": 0.35350382405858616, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003442922432389858 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_recall": 0.3188764804549842, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0029638694103824277 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_fmeasure": 0.31596377144440585, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0026655508139599173 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_precision": 0.1549567262980173, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002127947989131943 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_recall": 0.13893389284637747, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0018236049827216453 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_fmeasure": 0.13722355902976058, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016747877599416919 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_precision": 0.26952618807409345, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002533331450712522 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_recall": 0.24417509331372464, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.002199216476423094 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_fmeasure": 0.2408545283139996, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018742380511928072 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_precision": 0.2985654514117335, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029755296285733485 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_recall": 0.2693279956215855, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0025433959718711577 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_fmeasure": 0.26664577905196357, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0022767260952207273 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c45a8c8d98d51877063fa8ea347a7ac9b61c2235 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_gramatically_correct_text_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "bleu": 7.664142184014725, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.18311227507126876 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_precision": 0.3746709568888028, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0034292359840454125 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_recall": 0.3318290086834598, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0028931410590327202 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge1_fmeasure": 0.3315310557370324, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002595366438750264 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_precision": 0.16260171493807835, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002161100502458248 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_recall": 0.14326943676270018, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0018229254941988782 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rouge2_fmeasure": 0.14239753185765971, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016696513011695726 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_precision": 0.2835816428192323, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0025993635120059306 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_recall": 0.251337772350117, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0021560416701979584 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeL_fmeasure": 0.25032287278156323, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018610404732014262 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_precision": 0.31567282011474695, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0030093908891570794 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_recall": 0.2786749264473846, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0024797369016044467 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_gramatically_correct_text", + "rougeLsum_fmeasure": 0.27861256778529525, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0022359749139328443 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.json new file mode 100644 index 0000000000000000000000000000000000000000..1b708fa9983811202e64db65e578a1d37ec57b2d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 0.11176674048639335, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.025745526624568513 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.16696437758477956, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0017859239587553095 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.15714888553652667, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0014080404762761625 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.15222302512937821, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0013013498465447167 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.009953161364593704, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.00045153060703839287 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.011372231163400725, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.00047796121503254033 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.010123335458248412, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.00043360666103113316 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.12080392040996726, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.001200893081884765 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.11779742301789177, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0011408283583082188 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.11199161031913281, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0009318642813866649 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.15176134198199345, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0015534141731862994 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.14365210992596641, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0012440730468959943 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.13868103668142837, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0011150022939164787 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b974996fbae01f36f3f035d4450fc0453309ba42 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 5.3012905706855715, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.06983249125236993 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.3815413917530348, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.002837174970345969 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.3064552216042878, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0023886076473393645 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.32162747895375954, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020771074301500782 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.13086483275629, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0020280885765991885 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.1025349516561498, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001571669556321608 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.10817189459012165, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015550558960603117 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.27916128217581454, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0023638984947284046 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.2222943424941319, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0018853089294649107 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.23379701509505144, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0016853591821340379 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3136019413612245, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002623636065057541 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2503472789320967, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002117352162606577 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.26334461160376826, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019172374126938273 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.json new file mode 100644 index 0000000000000000000000000000000000000000..af227bd1038e8c7a57622ae0aa6029c4692cb4d2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 6.484621213756497, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.0974863563868723 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.41139978305209435, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003067700206274608 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.3252856106278531, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024570831951622046 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3420522066441051, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020985317696014232 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.16044952433810813, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022415019504744573 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.12295995789487724, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016908155548698506 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.12966947477583363, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016114647269419636 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.3101968039122714, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026559494676439695 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.2432211605884282, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0020134767570951996 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.25601590775495564, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017579676075034684 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.34330225686796983, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002884969316299285 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.26983375724985587, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002240579967780497 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2842749213664702, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001992190307244928 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ce095d174280973afff74f7ba44e4f979cd3c197 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 6.879629327338769, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1346069600960464 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.42201728977513014, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003107151077288339 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.3272628452554048, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002461890669832865 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3463166802954874, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.00213652320528259 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.17146778036168178, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0023302870066652893 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.12891634697023943, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017367276208110785 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.13691320451323, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016811203463266734 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.3213628033975934, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0027392401350909996 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.24620580859495172, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001997741786107464 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.2610757008973968, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017801310756353193 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3548763955773087, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029163728160237273 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2732798481620792, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022332299942385615 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2896766488362631, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001994600250845987 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bd3c0edf687f8ff199ca78a5193983a8e89aceea --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 7.043340928793498, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.17457577578396632 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.42849398140403416, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003154039113080988 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.3260253265844876, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024300314619900886 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3484130556989747, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021567720832225755 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.1755199620636604, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002326078614960514 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.12942494945873848, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017198177455500956 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.13896898011991943, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001696565627297103 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.3295172578321846, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0027851684130843772 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.24845018656704826, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.002015612153914146 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.26571281983219025, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018278399179337257 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3613892288819798, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.003004023862876739 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2729143969722366, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022213221391673625 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2923263218516018, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0020524443622954285 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.json new file mode 100644 index 0000000000000000000000000000000000000000..8544a246933a64d307df1ac450b67bd3b37f32ab --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_generate_text_restaurant_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 7.319824182452319, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.10193025707807249 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.44030532087327506, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031770242292659683 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.32784942801165234, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0023757237014025534 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.353385644913835, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020821634201849126 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.18788682322290728, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002464730672599637 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.13467537191827086, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001690154302772729 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.14603196173656227, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016877020428632365 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.3410417220866126, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0028515279745281513 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.25124499237542, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001976384646702889 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.27131741619623057, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017940658157043932 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3732999668515814, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.003040944777908066 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.27656091589535414, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002210511819363925 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.298421172979648, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0020128816004845508 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_0.json new file mode 100644 index 0000000000000000000000000000000000000000..3e19b33294f7ca56714b9ff60e0c8eecc937f920 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "bleu": 2.312044583390139, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.0395109885826077 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_precision": 0.1483234108399301, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0018820269691433504 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_recall": 0.2665312132559497, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0022782588706576823 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_fmeasure": 0.18396830789775534, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0019217889423799447 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_precision": 0.06330225911047903, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.000929977214652403 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_recall": 0.1144099347030503, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0013911841551972658 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_fmeasure": 0.07857762779721571, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0010324442678352934 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_precision": 0.13168588320305488, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0014088056357095735 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_recall": 0.24187944010259957, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001991719734240969 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_fmeasure": 0.16491978865694182, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0015173618055678087 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_precision": 0.13170067737530292, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.001562161536791986 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_recall": 0.2380165156086324, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0020441457742624673 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_fmeasure": 0.16382995952828802, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0016389684965023624 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_1.json new file mode 100644 index 0000000000000000000000000000000000000000..1343b87beb53b28469f0506c8b79d324c4856d3f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "bleu": 5.658373765079044, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.08499855577351746 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_precision": 0.3785635846368343, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0030612871591419147 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_recall": 0.30450164969564714, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0022564011527415394 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_fmeasure": 0.31664965729123945, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020607356438432697 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_precision": 0.13934496500807864, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.00216195315567069 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_recall": 0.10702848594772853, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0014968393936312507 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_fmeasure": 0.11238103667987336, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015100568087131015 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_precision": 0.28631430972883853, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002617927639070605 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_recall": 0.2283811920065958, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0018138508581349217 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_fmeasure": 0.2374686347495831, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0016753126850071298 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_precision": 0.31633107781620623, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0028315570567799433 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_recall": 0.25293146488273016, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0020207172248228092 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_fmeasure": 0.2632560786781301, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018894463768983068 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f5961014b2690b6af566e75b80cfc1e84cc38d0e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "bleu": 6.917215486681154, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.09030336208671559 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_precision": 0.40102908401240517, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031305165635581666 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_recall": 0.3245770394369534, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002380280848054982 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_fmeasure": 0.3365847325089085, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021240478562747096 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_precision": 0.1624015628216895, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022128114021614867 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_recall": 0.12717184459111075, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016440230921468948 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_fmeasure": 0.13240317910861094, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001585927980196938 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_precision": 0.3078746669304236, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026746765410402343 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_recall": 0.24821866410165572, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001975259655202282 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_fmeasure": 0.25697032555307603, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017681623995959028 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_precision": 0.3384966177161513, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002883629760587024 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_recall": 0.27305479728579, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0021713449800655122 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_fmeasure": 0.28336588654052414, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019832801111781904 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_3.json new file mode 100644 index 0000000000000000000000000000000000000000..944f64a407fe56ce8864e61d8b9485b9ad5d1ac6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "bleu": 7.302933244369964, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1527151661282377 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_precision": 0.40976641043825285, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003078900083587585 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_recall": 0.3298207802659436, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002370269980991039 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_fmeasure": 0.34292801400129946, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020983362895782443 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_precision": 0.16923415682313503, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022309657925827548 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_recall": 0.13169306775839348, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016574071058421535 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_fmeasure": 0.1375143860984762, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001597502116017482 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_precision": 0.31910429949813013, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.00271697238304695 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_recall": 0.25477988953379643, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001954868697916928 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_fmeasure": 0.26487498731759745, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017575023861850282 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_precision": 0.35002435680776456, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002909025689835447 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_recall": 0.27988532121673076, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002164775670324916 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_fmeasure": 0.2914768408781806, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019710026406425415 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_4.json new file mode 100644 index 0000000000000000000000000000000000000000..343d073a8337c3357debfdac7ec95e7165939399 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "bleu": 7.669963629530005, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.19346868748686652 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_precision": 0.41822864707123897, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031091354286543996 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_recall": 0.3361316604502726, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0023559546948861898 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_fmeasure": 0.34959289046921094, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020793186867037474 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_precision": 0.1737722798289324, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022559830525788267 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_recall": 0.13630282002247948, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.001690717470047277 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_fmeasure": 0.14197862193928545, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.001637642338037844 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_precision": 0.32559296595574067, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.00272622024383481 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_recall": 0.260656215712442, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019981009630238747 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_fmeasure": 0.270791556407417, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017960817490802496 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_precision": 0.3561490228639673, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002943695124328949 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_recall": 0.28548991550740394, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022090994833757244 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_fmeasure": 0.29703338834518844, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002014348371578559 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_5.json new file mode 100644 index 0000000000000000000000000000000000000000..5e90eca7437a9e68c0a266ded71ab71008f8b49a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_e2e_nlg_cleaned_text_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "bleu": 7.654080416990873, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.19571238370874128 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_precision": 0.4239353949486354, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031328799053710198 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_recall": 0.3346884409831521, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.00232049776848557 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge1_fmeasure": 0.35023251954607215, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002029722816220765 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_precision": 0.17998608899131224, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022646779528023306 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_recall": 0.1379401661329551, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016637853565731088 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rouge2_fmeasure": 0.14479391497677302, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016055061136987026 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_precision": 0.33239544579609576, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002774448505172659 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_recall": 0.2607705965299782, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001964723134792992 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeL_fmeasure": 0.2728400159017183, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017573515029372963 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_precision": 0.36254724652343057, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029613989798622157 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_recall": 0.28517595951447855, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0021666326647344194 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "text", + "rougeLsum_fmeasure": 0.29856008882369317, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001949304832193815 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.json new file mode 100644 index 0000000000000000000000000000000000000000..10859b49d22c9a3956b421d4d0a813f6ab27e6e9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_precision": 0.08601322052693357, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.001489727730411717 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_recall": 0.20924410822933326, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0034231335371689518 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_fmeasure": 0.12035436857080709, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0020099353839720534 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_precision": 0.01193354789546424, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0006397142671079087 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_recall": 0.029994300661093865, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001603282064351233 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_fmeasure": 0.016871170959750856, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0008961563503630702 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_precision": 0.07594233748050107, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.001192403250385716 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_recall": 0.1855080583745368, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002795393404522018 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_fmeasure": 0.10635833102686837, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016094140448635636 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_precision": 0.06979928841705295, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0012075993866203928 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_recall": 0.17170883890703695, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0029043246785420388 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_fmeasure": 0.09800348259551175, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0016526422289216889 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "bleu": 0.5989061497441678, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.04560411376477311 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.json new file mode 100644 index 0000000000000000000000000000000000000000..201f69b991b22fa90d86b3a08002e6a06aef54f2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_precision": 0.11774017314240483, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0019052567574435065 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_recall": 0.21726972418847335, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004161648851245577 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_fmeasure": 0.14265747670098736, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0022533103077694763 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_precision": 0.012105474988350063, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.000710088400602416 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_recall": 0.026644819771942975, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001646589314669167 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_fmeasure": 0.015898317357067135, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0009292567523827307 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_precision": 0.08871947393016015, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0014307460077157546 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_recall": 0.16050680730614136, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0029158160901583295 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_fmeasure": 0.10633984941798981, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0015849974450020952 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_precision": 0.09440999098393471, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0015075483157921815 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_recall": 0.1745714923938198, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0033720794167318327 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_fmeasure": 0.11432471005231339, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0017839300909078509 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "bleu": 0.8307325092609459, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.08101919299614214 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a11218ab02fc53b763c8b988ce6dde52f64cafac --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_precision": 0.11302706654940622, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0018593332628316893 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_recall": 0.2460436363471978, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0037872620423532104 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_fmeasure": 0.1481415675239767, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0021642331088208224 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_precision": 0.013053642716381332, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007155352294008017 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_recall": 0.03017269382059932, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0015996985516903391 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_fmeasure": 0.0174749223761466, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.000900127336792311 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_precision": 0.08299048940700292, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0014081479474376902 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_recall": 0.17954598888703394, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0026498882602493264 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_fmeasure": 0.1080255694309031, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0014919817019001394 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_precision": 0.08995434230427667, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0015144673716852113 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_recall": 0.19646935910004223, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0030868956085950226 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_fmeasure": 0.11778050548494788, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0017160843639228713 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "bleu": 0.7096901242580976, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.05577067558873664 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.json new file mode 100644 index 0000000000000000000000000000000000000000..25a5a14bf744675eeeff980a70af2c2b3a0f0bae --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_precision": 0.10499197275901183, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0019010472325354404 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_recall": 0.23424489218202285, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004151663117206758 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_fmeasure": 0.13993184120346575, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002395620259341809 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_precision": 0.013013272243975858, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007437340426547505 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_recall": 0.030512183916105506, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0016971799846190242 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_fmeasure": 0.01773853594640338, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0009780501520640062 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_precision": 0.07787068629627976, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0013947978353617287 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_recall": 0.17322899854212984, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0029625614134759564 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_fmeasure": 0.10336085541455355, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016861984554507592 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_precision": 0.08385124269644273, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0015454338092998716 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_recall": 0.1877925759738355, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0034402617687262706 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_fmeasure": 0.11170901074459809, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.001935231182288914 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "bleu": 0.7643563196224507, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.060516055001859886 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.json new file mode 100644 index 0000000000000000000000000000000000000000..af56a99df36532788e5dbe2818a5e2f7a0e1af45 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_precision": 0.029270950352660315, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0020065508927545363 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_recall": 0.054292494387326445, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0035095105726254796 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_fmeasure": 0.034205133663320925, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002130522101860963 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_precision": 0.004080736859560897, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0005900878496520041 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_recall": 0.007641895050367479, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.00097223815465809 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_fmeasure": 0.004783264838725394, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0006044566237329345 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_precision": 0.022370274339247025, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.001625959107979613 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_recall": 0.04008109112128974, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0025643726913754435 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_fmeasure": 0.025477711600550405, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0015794541340020175 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_precision": 0.023817663907487817, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0017123315453502917 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_recall": 0.04362025506139685, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.002869716532881049 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_fmeasure": 0.027411630968536074, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0017286334063830189 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "bleu": 0.29936737554664894, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.06333594224392126 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.json new file mode 100644 index 0000000000000000000000000000000000000000..8aac289fdda48713046f4c195c08cc1e540b4cae --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_boils_down_to_simple_idea_that_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_precision": 0.0008576329331046312, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0008576329331046343 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_recall": 3.1764182707578934e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 3.176418270757912e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge1_fmeasure": 6.125949522175937e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 6.125949522176127e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_precision": 0.0, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_recall": 0.0, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rouge2_fmeasure": 0.0, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_precision": 0.0008576329331046312, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0008576329331046343 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_recall": 3.1764182707578934e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 3.176418270757912e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeL_fmeasure": 6.125949522175937e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 6.125949522176127e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_precision": 0.0008576329331046312, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0008576329331046343 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_recall": 3.1764182707578934e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 3.176418270757912e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "rougeLsum_fmeasure": 6.125949522175937e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 6.125949522176127e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_boils_down_to_simple_idea_that", + "bleu": 0.0, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.0 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_0.json new file mode 100644 index 0000000000000000000000000000000000000000..938208f2a25cba5fc194d58c61746116b65d9332 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_precision": 0.08785520812835405, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0017998077566166923 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_recall": 0.21381700588328337, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004102874678024494 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_fmeasure": 0.12304686221145984, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0024384970755190246 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_precision": 0.01396692872396121, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007089258908322197 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_recall": 0.03497812070098322, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0017422549858707552 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_fmeasure": 0.019716305531943378, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0009850886667063586 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_precision": 0.073836479271441, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0013755441288147774 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_recall": 0.1810860810587385, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0032222426550226036 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_fmeasure": 0.103624513733133, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0018723555859277226 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_precision": 0.06797287037657533, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0014074123866873501 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_recall": 0.16720206816344646, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0033103712098051024 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_fmeasure": 0.0954563322396712, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019181008675671265 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "bleu": 0.6951449410126411, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.07649685778024824 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_1.json new file mode 100644 index 0000000000000000000000000000000000000000..a7fd98184d9137cc696417e0792df23a02c07fe7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_precision": 0.12486307177941995, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002333030764269263 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_recall": 0.17701443524540267, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0035983361097093195 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_fmeasure": 0.13551729087860911, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002244723695600438 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_precision": 0.01080484683339422, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0008615061540764822 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_recall": 0.01766476395873732, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001206171246859144 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_fmeasure": 0.012104885502617603, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0008081822477551506 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_precision": 0.0970099571674389, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0017837861435037988 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_recall": 0.135913907810521, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002573537485904688 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_fmeasure": 0.10464228517330777, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016250083581085943 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_precision": 0.09870668722966038, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.001839221923939297 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_recall": 0.13939382706838868, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.002824716995864924 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_fmeasure": 0.10680811423589318, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0017423671645419993 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "bleu": 0.6418362037219415, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.10975824216647798 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_2.json new file mode 100644 index 0000000000000000000000000000000000000000..1e160b7ffc624044ffb4a19bfc707f3400f36aaf --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_precision": 0.13693727131284883, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002867447164210865 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_recall": 0.1925058409582237, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.00344213336972596 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_fmeasure": 0.14570650267756477, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002378941385995561 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_precision": 0.015417250842210722, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.001067355594423882 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_recall": 0.02339412063589744, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0015128675685687942 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_fmeasure": 0.016540998688253494, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0010166295676320167 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_precision": 0.1092349946394738, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0022921046872309246 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_recall": 0.15434494177372146, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0026589145886085404 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_fmeasure": 0.11612824174493956, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0018217319112931597 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_precision": 0.10856158470399667, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0023269612772477415 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_recall": 0.152553343173584, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0027788394482328844 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_fmeasure": 0.11514154801275071, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018878468117351512 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "bleu": 0.8108179139657711, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.12705995346927912 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_3.json new file mode 100644 index 0000000000000000000000000000000000000000..29d6ddf618bf96a9c2618a7d374aaea2b886e24b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_precision": 0.13563786026465277, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0030566129634817477 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_recall": 0.18802799291524244, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.00357664038215709 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_fmeasure": 0.1426531931541618, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002586850906713085 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_precision": 0.017442792260430814, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.001100826746094403 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_recall": 0.026449724957200424, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0015566681933243279 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_fmeasure": 0.01889574180325777, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0010911361599695013 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_precision": 0.1079022009981362, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.002335404534765411 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_recall": 0.15167890991580765, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0028008093319595393 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_fmeasure": 0.1139215911001409, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0019571989970646572 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_precision": 0.10782682350987516, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0024013803164332965 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_recall": 0.15026311614000185, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0028973161396880012 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_fmeasure": 0.11339280362226653, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0020325791985732135 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "bleu": 0.8773649045212694, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.11660132941903724 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_4.json new file mode 100644 index 0000000000000000000000000000000000000000..f6539ca27728463ed79cc3ebac1150c66111fb11 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_precision": 0.04056265174869925, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0027356110529654534 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_recall": 0.050786036823568484, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003196010331614339 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_fmeasure": 0.040147604598473816, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002480690262574129 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_precision": 0.006607559048731122, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.001009742810903406 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_recall": 0.00849924754298773, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0010791020860047476 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_fmeasure": 0.006640579605150196, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0009022022003023071 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_precision": 0.03310929259525501, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.002243362243706627 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_recall": 0.04113526678175656, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002542893900861329 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_fmeasure": 0.032413930700901525, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0019512957708450456 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_precision": 0.033227844625563996, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0022608759002654445 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_recall": 0.04106024416303349, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0025628565510947927 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_fmeasure": 0.032497622810383237, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.001977165308187117 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "bleu": 0.22273027127435427, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.053862193531175 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_5.json new file mode 100644 index 0000000000000000000000000000000000000000..b47b876006ba8f3e9d742717de0a0eb7cc3b0b79 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_DOC_tldr_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_precision": 0.0028264204041118578, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0008349091404664074 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_recall": 0.002169808352873373, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0006083551170636029 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge1_fmeasure": 0.002408518357660293, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0006851091594038417 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_precision": 0.00029254180891250816, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.00015725543023099734 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_recall": 0.00020462820860040322, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.00011211479804596237 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rouge2_fmeasure": 0.0002397463551736582, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.00013033009573483993 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_precision": 0.0020221693154545543, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0005384638968072176 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_recall": 0.0016282149852303604, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0004451035213829608 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeL_fmeasure": 0.0017660754927783585, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.00047012290492895134 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_precision": 0.00218432680280627, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0006054710624941614 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_recall": 0.001726345399206282, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.00047538249577709987 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "rougeLsum_fmeasure": 0.0018882985436314338, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0005141685685603013 + }, + { + "task_name": "gem_xsum", + "prompt_name": "DOC_tldr", + "bleu": 1.1827594679031042e-43, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 4.377910669778258e-37 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..e36f78b5beb66c2eeb56436567243ca2f1ba9a11 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.1158071847580149, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0018165761216020508 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.28067020528577075, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004128869715644845 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.1620070178287433, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002441688281448867 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.019660583386168388, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.000745126629124706 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.04960567998718761, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0019206822821280743 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.02780910006627101, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.001048269259419271 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.08983266681131948, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0012376193912151856 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.21960260688104757, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0029450533082012067 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.1259092579196459, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016674239611603732 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.09018130758669934, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.001441468599655175 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.22079158054359857, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0034244847154332263 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.1264703650002751, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019559064654329516 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.9867298890552224, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.0636863740857457 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..6947b349c2949620a1c8dab3f23f1935a318ce66 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.12534579534327125, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.00193945618548172 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.27058957289695346, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0043828330597585445 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.16460140030448664, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0024490418088823833 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.01759280829959392, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0008355125639125885 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.04185140008866747, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0019643064430206994 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.024161160413064688, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011266352477578854 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.09368708847755541, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0013943909386695036 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.2019168442700265, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.003109796908751444 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.12258268240644458, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016862279472992232 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.09878883028828475, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0015789128996359261 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.21398695995793088, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.003606717868964285 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.12964372208686004, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019843558414494125 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.986334549008572, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.1026134280695105 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..6e0f556d130fe3624a2cfa2af78a646770f3aff7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.11833601279755995, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002199294284784323 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.24121068192166684, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004044710436865143 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.15079272411614866, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0024454125650679305 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.016827094361182786, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0008831709899277623 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.036633244517976074, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0018506466619519948 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.021955967558594934, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.001087239850414522 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.09217477971271017, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0016246776666746755 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.18812387120682225, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002891644059806244 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.11723212187021603, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.001714077795522329 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.09310810494075238, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.001750123872504354 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.1906145778565124, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.00328348190414569 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.1185738466895609, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019372106823996678 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.8510392504395363, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.06647941816704432 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..08cf1b47fdca01370d16912b2c120bb45238348d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.11511064720378139, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0024031770641084484 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.22827150593652096, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.00416286720206103 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.14375568998105198, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002550732075823139 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.016386126450038938, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0009430306754946043 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.03453203803155488, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0018851772654117098 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.020853724585447975, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011315789722664176 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.09095045508362522, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0018411782290517719 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.18142579882700435, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0031425768784492493 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.11360197423806047, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.001884854751254693 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.09156035684290141, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.00196609095636847 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.18238021901307033, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0034503657802804075 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.11426161274403947, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.002072690651007159 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.8650437116316979, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.08348862368049724 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..c89e9ba8ffb3946cc5d906a3b70dc7d587d42472 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.0361602458825991, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0025988245241512615 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.0581275939105786, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0035711432213003467 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.03860671254711545, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0022900584510195322 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.005992076983678361, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0011155187418557422 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.009962165254990031, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0011307954713829275 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.006231843463345877, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0007012509924568781 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.03038144486746073, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0023281897845746865 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.04731308569695526, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0028495942670980546 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.031530683354832556, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0018296711578288528 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.030582547849958886, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.002360088780868479 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.047711987788717505, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.002969080473622203 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.03178346574583942, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.001898518321849197 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.41795248569633103, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.084171862077561 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..095343a9da4871c53acec12b370272724e61c2d8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_article_DOC_summary_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.00282366128721056, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0007697832157484954 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.002365813329267624, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0006488826359222657 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.002527603190035361, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.00068757084609251 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.000252945660825794, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0001130835622425815 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.0001820087669144273, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 8.275145912995973e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.00020969228861543636, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 9.41768743666813e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.0020324491777993737, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0005401952082914505 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.001705553553343957, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.00045030351383285445 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.0018180833551753694, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0004787735421768299 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.002125879390906554, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0005641336556569049 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.0017893614930695643, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0004747147768544628 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.0019064161369800514, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0005036949386606113 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 8.059349929930117e-40, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 3.4078462014416495e-34 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a3d46d42bff1fd256769262c1ed240d01cb997b5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_precision": 0.09959661209849045, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.001720794675352159 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_recall": 0.24296043524964275, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003922924238883301 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_fmeasure": 0.1394877149729816, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0023191928763038917 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_precision": 0.015676753241847172, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.000696440808966843 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_recall": 0.03949985958379005, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001763700865011535 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_fmeasure": 0.02216490573223825, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0009754645017508243 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_precision": 0.08380837589550291, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0012762456181644143 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_recall": 0.20538014455763795, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002967340337812102 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_fmeasure": 0.11748646473161478, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0017149795760748592 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_precision": 0.07649621759728135, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0013213921725338553 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_recall": 0.18872305812070983, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0031571885489383726 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_fmeasure": 0.10747916740229993, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018034915409559326 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "bleu": 0.7657539744351544, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.05960388643906178 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_1.json new file mode 100644 index 0000000000000000000000000000000000000000..65e9d76f1aafff6e019d8dd033de0b34513c21a6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_precision": 0.10779079125778714, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0017364689097811245 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_recall": 0.2531343205060018, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003849102811710255 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_fmeasure": 0.14786528609926117, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0022472583600236513 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_precision": 0.01717373699792966, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0008086755123805268 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_recall": 0.04258571346118677, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001990619230673135 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_fmeasure": 0.024050432775105567, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011119514244593799 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_precision": 0.08616745994892451, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0012884289488737097 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_recall": 0.20370042941588284, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002916372748330544 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_fmeasure": 0.11829636533500087, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.001646799217950579 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_precision": 0.08416622990633002, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0014043090246987175 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_recall": 0.1990339703496491, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0031810082266012984 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_fmeasure": 0.11550772215317513, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018112100752252266 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "bleu": 0.9744864699598849, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.0715803104250675 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a29174bd442ae4b55bb14c40b853242b367ba699 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_precision": 0.09974253383196298, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0016508496308147503 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_recall": 0.24044895366223354, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003610084224116856 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_fmeasure": 0.13806182767970213, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0021135695098749214 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_precision": 0.015474430089813513, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.000760295961817625 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_recall": 0.0390759843386084, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0019080665242204116 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_fmeasure": 0.021850132907452764, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.001062000791042869 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_precision": 0.08367374656252795, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0012812689380292408 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_recall": 0.20304267063542045, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0028755638811545294 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_fmeasure": 0.11603612234525328, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016404618326966145 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_precision": 0.07733059958801149, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0013169092247786304 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_recall": 0.1882421408340462, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0029988980863709493 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_fmeasure": 0.10727262095783592, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0016997810733515313 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "bleu": 0.8347136741256534, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.062076277683922425 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3ae396f2e4d2883dc657dabeec06380593bb3d28 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_precision": 0.09689033249970055, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0018810183346657067 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_recall": 0.2240723175463038, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003898850764408054 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_fmeasure": 0.13115011437349358, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002301574585288779 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_precision": 0.014805074825435426, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007813933511829814 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_recall": 0.035775335550481645, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0018150201824477363 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_fmeasure": 0.020384730084258812, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.001038756802634804 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_precision": 0.08180231716848364, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.001509999290109991 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_recall": 0.19020520762940066, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.003130840716495653 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_fmeasure": 0.11089421988144217, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0018199727364072546 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_precision": 0.07516233715156442, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0014943501606461884 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_recall": 0.17573853870134074, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0031552844726888797 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_fmeasure": 0.10193009295990486, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018015834348326844 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "bleu": 0.8124291106760078, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.07588482930693484 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_4.json new file mode 100644 index 0000000000000000000000000000000000000000..82e97203d3cad14b95fc4ed1f40ee0c0105e8600 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_precision": 0.03575664714500481, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0024098528232116526 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_recall": 0.060819442484463054, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003534881031726274 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_fmeasure": 0.03985059812853305, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0022760105727489804 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_precision": 0.005750259558436412, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0006358449659266129 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_recall": 0.011282915311051312, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0011299755593093203 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_fmeasure": 0.007018029042731219, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.000685007347774824 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_precision": 0.030116615236100916, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0021214097977901845 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_recall": 0.05019883302718781, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0028798226137028322 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_fmeasure": 0.032959125867263926, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.001860506762679618 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_precision": 0.02960913737630851, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0021194541107393936 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_recall": 0.049340056932530726, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0029147509307593054 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_fmeasure": 0.032337968793062846, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018663100809540166 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "bleu": 0.5188346596881508, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.1162647822321323 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_5.json new file mode 100644 index 0000000000000000000000000000000000000000..2653e3f40a1a5d72028947c276c2bdbe0c9ea600 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_DOC_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_precision": 0.0027970449110702633, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0008129954674738013 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_recall": 0.0024652900122106723, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0007379988663176068 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge1_fmeasure": 0.00257629662639923, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0007584585077324427 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_precision": 0.000261704167087075, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.00017583118303625035 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_recall": 0.00027915111155954665, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0001876136151566084 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rouge2_fmeasure": 0.00027004452530749476, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.00018148779778783585 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_precision": 0.002311528640826497, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0006531263217620076 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_recall": 0.0020110161874394208, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0005684052414990399 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeL_fmeasure": 0.002111652191363848, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0005941763033496732 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_precision": 0.002412426632956454, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0006907319147059392 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_recall": 0.002115676852444913, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0006160449658742334 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "rougeLsum_fmeasure": 0.002214671104382056, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0006380204218087325 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_DOC", + "bleu": 6.894559936640943e-38, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 5.078171225423703e-32 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.json new file mode 100644 index 0000000000000000000000000000000000000000..711c9f8c06718a7eca52b7a0ebc652390e7da2c7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_precision": 0.10766417393148146, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0017247775348159335 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_recall": 0.26220045752079946, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003975340578476309 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_fmeasure": 0.15080495502999547, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0023292636824101256 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_precision": 0.018011700797613012, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007071056250652039 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_recall": 0.045671998488902174, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0018504317904469703 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_fmeasure": 0.02550920276281168, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0010004591177405439 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_precision": 0.08803820960705872, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0012435040927227102 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_recall": 0.21591728450361894, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0029447735431074496 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_fmeasure": 0.12351381489334008, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016767094669245285 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_precision": 0.08357513379135657, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0013517986553990002 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_recall": 0.20562438203051336, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.00324355265235417 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_fmeasure": 0.11739126743954412, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018454058790702413 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "bleu": 0.9053200662535719, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.08304303167521133 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.json new file mode 100644 index 0000000000000000000000000000000000000000..91bcf5b8f677cf3f60691cd72493ab887850b9c0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_precision": 0.12366225220702332, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0019035992000767568 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_recall": 0.2746639885726219, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004363644416585785 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_fmeasure": 0.16458352372455684, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0024404180174069736 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_precision": 0.01831848136320181, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0008613493134626757 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_recall": 0.044642681354896206, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0020693469381105048 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_fmeasure": 0.0254681124378878, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011760381453017 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_precision": 0.09283957435911433, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0013633579746673554 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_recall": 0.20656882824913186, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0031972954373685456 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_fmeasure": 0.12335078113747294, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0017240156359532798 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_precision": 0.09649134174288254, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0015227636340121218 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_recall": 0.21532151284750878, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0035949140524341836 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_fmeasure": 0.12839142485622748, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019623450564247953 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "bleu": 1.0517549411798284, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.08869197714127522 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.json new file mode 100644 index 0000000000000000000000000000000000000000..b7d70ee939ab3e61fc1c0048fa2e9408b9773f66 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_precision": 0.11477590393567126, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002116330005854684 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_recall": 0.24394235435709302, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004069202937893897 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_fmeasure": 0.1489043126868222, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002414057619883924 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_precision": 0.017617469606827755, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0009209461630191176 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_recall": 0.039942432060720914, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0020431563227289234 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_fmeasure": 0.02344635398091455, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011875761392866745 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_precision": 0.09141125984419861, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0016082349170530377 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_recall": 0.1955280825356397, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0030928571079126945 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_fmeasure": 0.11876289392440431, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0017958651709665465 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_precision": 0.08991259226184872, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0017045288942889236 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_recall": 0.1921527798348713, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.003343896055475177 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_fmeasure": 0.11666161719412536, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019395954814823589 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "bleu": 0.9359180990331135, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.097313852367643 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.json new file mode 100644 index 0000000000000000000000000000000000000000..7344c3227093c13e7417669240b7f627704b7ed0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_precision": 0.10967477103152969, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002373361239237867 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_recall": 0.22921698427745044, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004179760492319134 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_fmeasure": 0.14143975183431184, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002624919098315165 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_precision": 0.01649113601256011, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0009108210651028919 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_recall": 0.03621079704469094, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0019138662731944262 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_fmeasure": 0.021683379341115812, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011414403236527958 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_precision": 0.08842314517868648, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0017879328745720076 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_recall": 0.18710793878265647, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.003197890711089028 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_fmeasure": 0.11452190311765521, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0019555924223011788 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_precision": 0.08585520766581471, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0018884567405713097 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_recall": 0.1806032948250851, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.003410584937322093 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_fmeasure": 0.1108174940054984, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.002093506046561213 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "bleu": 0.8545144299660299, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.08062058614293066 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.json new file mode 100644 index 0000000000000000000000000000000000000000..51943ad8fe6f9380b9f93907ab9275bfc1438856 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_precision": 0.033523252947635904, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002262808835339776 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_recall": 0.05524121400042497, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.003532082798269108 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_fmeasure": 0.037197403374487924, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0022954634096379305 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_precision": 0.0051584458678752216, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0007026116069116543 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_recall": 0.009635922855585887, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0012421025115398562 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_fmeasure": 0.006054078203169595, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0007863768658417492 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_precision": 0.028324453021289078, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.001994218364384606 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_recall": 0.045582045072611516, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0028859350433643343 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_fmeasure": 0.030859284839692826, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0019074776816356488 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_precision": 0.028190743604595166, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0020193479074785987 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_recall": 0.04530859399363896, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0029471761234043025 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_fmeasure": 0.030639007644487726, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019336596995026226 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "bleu": 0.41550983722811713, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.11383336021662172 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.json new file mode 100644 index 0000000000000000000000000000000000000000..6d3d27332d36181810554c038000efbaaa0f536e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_gem_xsum_summarize_this_DOC_summary_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_precision": 0.0031446540880503146, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0010851526656093654 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_recall": 0.0004018246904679879, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0001360401158331796 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge1_fmeasure": 0.000708246579679391, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.00023949778866834165 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_precision": 0.0004288164665523156, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0004288164665523165 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_recall": 2.858776443682104e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 2.8587764436821168e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rouge2_fmeasure": 5.360205831903945e-05, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 5.3602058319039565e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_precision": 0.0031446540880503146, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0010851526656093654 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_recall": 0.0004018246904679879, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.0001360401158331796 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeL_fmeasure": 0.000708246579679391, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.00023949778866834165 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_precision": 0.0031446540880503146, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0010851526656093654 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_recall": 0.0004018246904679879, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0001360401158331796 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "rougeLsum_fmeasure": 0.000708246579679391, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.00023949778866834165 + }, + { + "task_name": "gem_xsum", + "prompt_name": "summarize_this_DOC_summary", + "bleu": 0.0, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.0 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_0.json new file mode 100644 index 0000000000000000000000000000000000000000..32ea94afa50b26562bbaa60ae5176f2accf565d5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "bleu": 5.044003528820165, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.22920626380593712 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_precision": 0.08223335503910409, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0024516571009502493 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_recall": 0.6043317835131486, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.007310140932058555 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_fmeasure": 0.13070246265270175, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.003003328865094663 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_precision": 0.06021814295664582, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002303597081892545 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_recall": 0.44232864311481884, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.008135472118435535 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_fmeasure": 0.09519041983155013, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.002905103095548517 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_precision": 0.07970090960055028, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002390776645143582 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_recall": 0.5915829369519617, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.007434090945267709 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_fmeasure": 0.1270728154104261, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0029857125025585436 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_precision": 0.07898279807795379, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0024089195054829956 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_recall": 0.5841163781141749, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.00745835270564824 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_fmeasure": 0.125629974165267, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002984884476068228 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_1.json new file mode 100644 index 0000000000000000000000000000000000000000..71ca8b6116256e9f47ba31c6b92a2b173de200b2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "bleu": 10.987284589298396, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.6228982805404496 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_precision": 0.3018921785857166, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.007592424912559347 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_recall": 0.34032411186465444, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.007665397277299667 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_fmeasure": 0.27365913419935356, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.007178789576035563 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_precision": 0.182995294256973, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.007121557687340213 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_recall": 0.2131172886544418, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0073735162438965775 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_fmeasure": 0.1734691615853129, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.006761885716826925 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_precision": 0.2866580016638699, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.007545348452121212 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_recall": 0.3272517692490847, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.007719965820540302 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_fmeasure": 0.2617978649064106, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.00719744805064835 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_precision": 0.29054400425577176, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.007575454546327207 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_recall": 0.3290770238121191, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.007681543530250764 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_fmeasure": 0.26419466018780496, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.007189020162760364 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_2.json new file mode 100644 index 0000000000000000000000000000000000000000..093dbc069d2ab823c057703635e7b62aa2171bf7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "bleu": 13.894511213158287, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.8739525580726594 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_precision": 0.3962235671288584, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.008329795251643627 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_recall": 0.44796823076786213, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.008022473299790518 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_fmeasure": 0.3674980198284435, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.00787898395002465 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_precision": 0.27084269853025533, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.008065996347205293 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_recall": 0.31137177426270085, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.008133141525352511 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_fmeasure": 0.25734856308354354, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0076839950683234475 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_precision": 0.37925499641508387, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.00832851687783064 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_recall": 0.4342613524811934, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.008157597971122069 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_fmeasure": 0.3543621394489363, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.007955653293849538 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_precision": 0.3822857138351711, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.008360452943863943 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_recall": 0.4342525578898354, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.008116059673105629 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_fmeasure": 0.3559552758288509, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.007950933392077896 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_3.json new file mode 100644 index 0000000000000000000000000000000000000000..5c3cf88227a22ec525f1b9469684f397212b221e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "bleu": 16.302962969684817, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 1.0914160471683245 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_precision": 0.44754150572005014, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.008508724146964648 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_recall": 0.4928656980785378, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.007959264981992405 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_fmeasure": 0.4159209145067388, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.008066180840731338 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_precision": 0.31950165407284764, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.008430696030852732 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_recall": 0.35405055947121816, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.008289900831830925 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_fmeasure": 0.30169097752148116, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.008003118328318673 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_precision": 0.4296491063999405, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.008545775185136658 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_recall": 0.47866238354613455, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.008119911722901458 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_fmeasure": 0.4021318671912827, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0081642603534126 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_precision": 0.43342040994924064, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.00856185501876351 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_recall": 0.47874998363575016, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.008081456218781254 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_fmeasure": 0.4041172336659238, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.008150961646219602 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_4.json new file mode 100644 index 0000000000000000000000000000000000000000..24043508ec824bd0d863630c29cc79754e6eeeae --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "bleu": 18.29568798498642, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.8400045952338919 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_precision": 0.47003616790222097, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.008492394610500243 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_recall": 0.5070618235168789, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.008034196403817398 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_fmeasure": 0.440913771806968, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.008161084155097175 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_precision": 0.34267924080360035, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.00849291013938346 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_recall": 0.3721650196784438, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.008345501652871087 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_fmeasure": 0.32589784419427137, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.008140627546699501 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_precision": 0.4545619116360723, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.008535490921376865 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_recall": 0.49441236285200274, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.008175372919559136 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_fmeasure": 0.42864556356106626, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.00825295711841848 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_precision": 0.4575870105061546, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.008542975114188618 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_recall": 0.4951955460109368, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.008149833461155942 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_fmeasure": 0.430525903474684, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.008241357230569303 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_5.json new file mode 100644 index 0000000000000000000000000000000000000000..50d5993fcc0efeabe62e2f909603088cc6290890 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_Correct-the-solution_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "bleu": 19.563665938000955, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.830837212255332 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_precision": 0.4850213774986562, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.008412810347685195 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_recall": 0.5175895233206349, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.007925276186417592 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge1_fmeasure": 0.45358632651135367, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.008079574036676742 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_precision": 0.35233139121336177, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.008496659674238034 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_recall": 0.37841523275236855, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.008335884723129022 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rouge2_fmeasure": 0.33520179328257893, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.008136267592204509 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_precision": 0.46894629707993607, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.008460443723532397 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_recall": 0.5041604671316591, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.008082489163576902 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeL_fmeasure": 0.44099249707631255, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.00818874543924558 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_precision": 0.4720370238207721, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.008475086337406505 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_recall": 0.5048483591695989, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.008038036370329855 + }, + { + "task_name": "piqa", + "prompt_name": "Correct the solution", + "rougeLsum_fmeasure": 0.442736079453689, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.008170530134058251 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.json new file mode 100644 index 0000000000000000000000000000000000000000..375fa1673d9d149ae2ec3160462017d4e8e06702 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc": 0.49075081610446136, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011663828032649183 + }, + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc_norm": 0.49075081610446136, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011663828032649183 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.json new file mode 100644 index 0000000000000000000000000000000000000000..4da65230f21080025544c7f57a09b04be3065d9d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc": 0.5021762785636561, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011665713661738877 + }, + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc_norm": 0.5021762785636561, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011665713661738877 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.json new file mode 100644 index 0000000000000000000000000000000000000000..9b158dacbc628326ef6345751ad35fd703d7c76f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc": 0.5043525571273123, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011665382144642399 + }, + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc_norm": 0.5043525571273123, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011665382144642399 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.json new file mode 100644 index 0000000000000000000000000000000000000000..ed314ce210c7bb7c890389d83f1efca624c64a02 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc": 0.5016322089227421, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011665762007194866 + }, + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc_norm": 0.5016322089227421, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011665762007194866 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.json new file mode 100644 index 0000000000000000000000000000000000000000..3846ef4b2dbc6e00271af88eaca809983703e8b1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc": 0.5048966267682263, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011665264730078137 + }, + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc_norm": 0.5048966267682263, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011665264730078137 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.json new file mode 100644 index 0000000000000000000000000000000000000000..6d49285e0111b9c17d2daa0979f3930c46a0c69c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_choose-the-most-appropriate-solution_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc": 0.514145810663765, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01166115447552484 + }, + { + "task_name": "piqa", + "prompt_name": "choose the most appropriate solution", + "acc_norm": 0.514145810663765, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01166115447552484 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_0.json new file mode 100644 index 0000000000000000000000000000000000000000..a5686658cd4376a4b8ce2f5f5734ffb9ff7da9b7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_0.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "bleu": 0.08644025412923256, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.009820950909340235 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_precision": 0.022663125514556327, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0013513829670530827 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_recall": 0.1592144653136851, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.003449871907818082 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_fmeasure": 0.031036089835208214, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0009813521147527423 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_precision": 0.003241010643234634, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0004333769961243567 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_recall": 0.021524339394750014, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0013450358010657275 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_fmeasure": 0.004256247232539841, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.00034400170235730353 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_precision": 0.020762352004530072, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0012497895941737545 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_recall": 0.1502718739661574, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.003305027485971818 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_fmeasure": 0.028702267430638435, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0009058455781743254 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_precision": 0.01933761544810985, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0012600611343390243 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_recall": 0.1362003183642396, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.00300408432276789 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_fmeasure": 0.025974232921307155, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0008611143023707996 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_1.json new file mode 100644 index 0000000000000000000000000000000000000000..0b09ec2afc5487eaef012791a472567b84f37526 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_1.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "bleu": 0.14304039520961487, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.020196407881148105 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_precision": 0.053711187417481356, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0029279067285896583 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_recall": 0.09582097083032212, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.00324411522349448 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_fmeasure": 0.04722334546545548, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020880436511264647 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_precision": 0.009321490289307479, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.000928495984049966 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_recall": 0.013837525790323843, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0011119759768626336 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_fmeasure": 0.007609013308850757, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0006822487640430323 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_precision": 0.04649502848369309, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.00254016005961217 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_recall": 0.08725521239472234, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0030082346793116844 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_fmeasure": 0.04129383170227979, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018149259520630428 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_precision": 0.04637512898059172, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0025849567246808763 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_recall": 0.08219775751795474, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0028538866420825446 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_fmeasure": 0.0403293623763229, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018133499923210787 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_2.json new file mode 100644 index 0000000000000000000000000000000000000000..3133465dea2510d96a2d8bb7e581259493512df2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_2.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "bleu": 0.2608651316164953, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.03978730347320043 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_precision": 0.05429344326618384, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0029969628817093107 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_recall": 0.05806614564935589, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0027269030308790685 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_fmeasure": 0.04266745301669875, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002122467346772042 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_precision": 0.008207881019302006, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0010086514951802858 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_recall": 0.008521702795534656, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0010434649664570375 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_fmeasure": 0.006554418985992436, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0007815781854311512 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_precision": 0.04597127256330522, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0025493206390164915 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_recall": 0.051020708361635456, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0024526062149060925 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_fmeasure": 0.036366524875545106, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018289351480190433 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_precision": 0.04719764857087024, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0026618730300778984 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_recall": 0.050823488012879496, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0024311881894851393 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_fmeasure": 0.03690636788662361, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018560807675874356 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_3.json new file mode 100644 index 0000000000000000000000000000000000000000..d273b381cea895fdc87dbed5e56c15c361b2332e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_3.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "bleu": 0.22144147011965754, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.05131138433756984 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_precision": 0.058386033932004415, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0030880102581303886 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_recall": 0.05486532333879447, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002608469514368819 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_fmeasure": 0.04452655769234325, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021712328467205486 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_precision": 0.008602699160749428, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0009813451014566705 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_recall": 0.007308424504803039, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0008927033877862982 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_fmeasure": 0.006348389170194352, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0007281347015003358 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_precision": 0.05007522678633194, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026478813192163213 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_recall": 0.048399277860299794, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0023392317754922483 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_fmeasure": 0.038296677712480076, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018715868727211123 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_precision": 0.05143163493997383, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0027770376467427965 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_recall": 0.04819611262496829, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0023229320235610062 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_fmeasure": 0.038779230929206605, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001893632110275806 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_4.json new file mode 100644 index 0000000000000000000000000000000000000000..5536b39684002fa6c4b3fcc2ea71def7fe5b3686 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_4.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "bleu": 0.18473186157561908, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.04072950696800683 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_precision": 0.06712446822614468, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0033160597701479893 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_recall": 0.06019191056988439, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002736892229053133 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_fmeasure": 0.05159212402267852, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0023638676475464648 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_precision": 0.00964919360937356, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0010051600074264555 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_recall": 0.008577476981962201, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0009456245783267479 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_fmeasure": 0.0074306129720465705, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0007606984807758116 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_precision": 0.05818637904982665, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0029044534046547958 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_recall": 0.05347769921709429, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0024762222522701598 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_fmeasure": 0.045035878449402864, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.002091652415092048 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_precision": 0.059446564318682005, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029928762915145727 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_recall": 0.0537919766565263, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0024838459656666596 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_fmeasure": 0.04570769475572357, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0021186626160801304 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_5.json new file mode 100644 index 0000000000000000000000000000000000000000..d291b563c0979ef3758280c7fabd4a2e61bf75ba --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_no-prompt-needed_5.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "bleu": 0.3674534532595343, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.044535440751908385 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_precision": 0.06632940430625783, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003221290438735765 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_recall": 0.06301059430183462, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0028293221861692515 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge1_fmeasure": 0.05237001461800124, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002390063573522162 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_precision": 0.010990734326689173, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0011480661925135293 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_recall": 0.010346369422141026, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0010512298188535155 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rouge2_fmeasure": 0.008657019208894664, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0008613172115835112 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_precision": 0.05733867044052891, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.002753785198676713 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_recall": 0.056005566309979465, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0025635471231317537 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeL_fmeasure": 0.045594480368473495, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0020873498805373575 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_precision": 0.05908856304665778, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029043642978511183 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_recall": 0.05634193274869875, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0025654170882293886 + }, + { + "task_name": "piqa", + "prompt_name": "no prompt needed", + "rougeLsum_fmeasure": 0.046277441891386925, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0021092213962826474 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_0.json new file mode 100644 index 0000000000000000000000000000000000000000..9fbf26960a618e542aae2643e39622d40d37cd83 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc": 0.49510337323177367, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01166526473007815 + }, + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc_norm": 0.49510337323177367, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01166526473007815 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_1.json new file mode 100644 index 0000000000000000000000000000000000000000..0b8b330ed3bd99c59f962e874120436eb1b6e081 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc": 0.5038084874863983, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.0116654857447468 + }, + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc_norm": 0.5038084874863983, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.0116654857447468 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_2.json new file mode 100644 index 0000000000000000000000000000000000000000..11afbca9533bee416c99070fac51d5ba758c11dc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc": 0.4956474428726877, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011665382144642383 + }, + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc_norm": 0.4956474428726877, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011665382144642383 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a5546e6d26e02da146f766f1c5ad24484e57ff84 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc": 0.5250272034820457, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011651200967623707 + }, + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc_norm": 0.5250272034820457, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011651200967623707 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_4.json new file mode 100644 index 0000000000000000000000000000000000000000..6aca21a562f42fbddc8413a356e1944810afd352 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc": 0.5239390642002176, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01165244562107926 + }, + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc_norm": 0.5239390642002176, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01165244562107926 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_5.json new file mode 100644 index 0000000000000000000000000000000000000000..9b57ce2d65744835bcc165ba1ec1bcb74cb5d1aa --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_pick_correct_choice_index_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc": 0.5076169749727966, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011664470424044976 + }, + { + "task_name": "piqa", + "prompt_name": "pick_correct_choice_index", + "acc_norm": 0.5076169749727966, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011664470424044976 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..fe99bc5de1cbc70bd8313a9409835c51be0a86c6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc": 0.5233949945593036, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01165304715592779 + }, + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc_norm": 0.5250272034820457, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011651200967623706 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..616c2ba1183b4281527843bc786a1ba9b1b74d34 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc": 0.5212187159956474, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011655314732288858 + }, + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc_norm": 0.5223068552774756, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011654208652596474 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..acf26f11643df0d66227f0b3b3b242f7a8a25297 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc": 0.5255712731229597, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011650557844573578 + }, + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc_norm": 0.5163220892274211, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011659606710151779 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..6217605de146840b88866e9c66a757cf4553925e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc": 0.5206746463547334, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011655846995729703 + }, + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc_norm": 0.5163220892274211, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011659606710151779 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..63a387e3beb833e9417bbc8b5828f83bda2e6c7e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc": 0.5195865070729053, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01165686997928846 + }, + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc_norm": 0.514145810663765, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011661154475524835 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..9d17117ddf57210bd56e596cb1b0aa9d0d349a56 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_piqa_what_is_the_correct_ending_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc": 0.5125136017410229, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.011662170084916892 + }, + { + "task_name": "piqa", + "prompt_name": "what_is_the_correct_ending", + "acc_norm": 0.5081610446137106, + "dataset_path": "piqa", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.011664270112244223 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b8238dbfde668a3b59659f775cbcff676940e827 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc": 0.365, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015231776226264914 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc_norm": 0.36, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015186527932040122 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.json new file mode 100644 index 0000000000000000000000000000000000000000..b2d6941c1f463ee7c91254306e5b3799e437954d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc": 0.393, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015452824654081496 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc_norm": 0.388, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015417317979911076 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.json new file mode 100644 index 0000000000000000000000000000000000000000..19893a23cdeaa33e209d307c05cfde60206d992c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc": 0.386, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015402637476784385 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc_norm": 0.387, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015410011955493932 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.json new file mode 100644 index 0000000000000000000000000000000000000000..83f93b10db6f10b30fdec1ed25e1486fe6af01c8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc": 0.383, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01538010232565271 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc_norm": 0.379, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01534909100222535 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e2d44ff450014a3e6e02ce98a6618aee70ed7565 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc": 0.393, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015452824654081496 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc_norm": 0.388, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015417317979911076 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.json new file mode 100644 index 0000000000000000000000000000000000000000..3a069f3f7125bcee0b52a9c42b571a9e4cdb04d3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question-(Closed-Book)_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc": 0.384, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015387682761897068 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question (Closed Book)", + "acc_norm": 0.388, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015417317979911077 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d5c7cf2acc6d7b6cc454f10d0329f71ba50ef744 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc": 0.663, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014955087918653595 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc_norm": 0.567, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01567663091218133 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_1.json new file mode 100644 index 0000000000000000000000000000000000000000..5cf83a06d26bbbb226ac865a4dd8da8d22054f3d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc": 0.715, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014282120955200485 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc_norm": 0.648, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015110404505648661 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_2.json new file mode 100644 index 0000000000000000000000000000000000000000..05397c46121ba4658a9f767f7d9783234c0450da --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc": 0.71, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.01435639599990569 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc_norm": 0.664, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014944140233795023 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_3.json new file mode 100644 index 0000000000000000000000000000000000000000..1f2fe8afa0c4a970e31a241879ebbf3484abbd02 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc": 0.722, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014174516461485265 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc_norm": 0.682, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014734079309311901 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_4.json new file mode 100644 index 0000000000000000000000000000000000000000..06a9a374d173ab00299f1f00db132b7f21745dcb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc": 0.724, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014142984975740668 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc_norm": 0.7, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01449862787336143 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e5adba0afa265d8c445ac64f1b1df0f76b026e1f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Direct-Question_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc": 0.728, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014078856992462621 + }, + { + "task_name": "sciq", + "prompt_name": "Direct Question", + "acc_norm": 0.695, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014566646394664382 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.json new file mode 100644 index 0000000000000000000000000000000000000000..ba155aa4fb9a7bcf08b4d6b38b061857c926c5be --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc": 0.372, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015292149942040577 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc_norm": 0.347, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015060472031706618 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.json new file mode 100644 index 0000000000000000000000000000000000000000..e3fd3f9759bc87f25314dcecb0769ac49e51d2f1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc": 0.32, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014758652303574874 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc_norm": 0.329, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014865395385928362 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.json new file mode 100644 index 0000000000000000000000000000000000000000..0b1aa6e85cce748f1f7caf7e851e389bdda949b7 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc": 0.276, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014142984975740668 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc_norm": 0.291, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014370995982377946 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.json new file mode 100644 index 0000000000000000000000000000000000000000..461268237d467d1e72553ff22f74980d6d7d5aec --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc": 0.3, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014498627873361425 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc_norm": 0.308, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01460648312734276 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.json new file mode 100644 index 0000000000000000000000000000000000000000..036c8f2c961edfe1caaed2dbcf9dc67c1f2b30f6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc": 0.306, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014580006055436965 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc_norm": 0.331, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01488827258820393 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.json new file mode 100644 index 0000000000000000000000000000000000000000..012a9e0dd2e8727f5019937ec8d609a1fff91d2c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-(Closed-Book)_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc": 0.298, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014470846741134722 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice (Closed Book)", + "acc_norm": 0.308, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014606483127342763 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2c86b1e73ebe04d70dfbbfa6e1777de7e96ad8df --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc": 0.516, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015811198373114878 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc_norm": 0.434, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015680876566375058 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.json new file mode 100644 index 0000000000000000000000000000000000000000..4520f6a653e17f6b2e976788cf80f928a47201eb --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc": 0.395, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015466551464829342 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc_norm": 0.406, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015537226438634602 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.json new file mode 100644 index 0000000000000000000000000000000000000000..b3990b078a083c10cddf454fb0b805a52602bc6d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc": 0.323, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014794927843348632 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc_norm": 0.324, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014806864733738859 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.json new file mode 100644 index 0000000000000000000000000000000000000000..93a24ebb456b73057450df740ed6b3cba2f2b7cf --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc": 0.319, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014746404865473494 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc_norm": 0.329, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014865395385928357 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.json new file mode 100644 index 0000000000000000000000000000000000000000..b7b3e9982d43a969b54610560327445a82188631 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc": 0.322, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014782913600996664 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc_norm": 0.327, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014842213153411247 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.json new file mode 100644 index 0000000000000000000000000000000000000000..f2203b70082241c10cf19a4e6d033d325822de66 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice-Question-First_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc": 0.313, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014671272822977881 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice Question First", + "acc_norm": 0.309, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014619600977206482 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_0.json new file mode 100644 index 0000000000000000000000000000000000000000..2a18f7fd611a258e65e4d8b8c5b278d1d1d54e5c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc": 0.482, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.015809045699406728 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc_norm": 0.438, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01569721001969469 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_1.json new file mode 100644 index 0000000000000000000000000000000000000000..5f471b2de9d75fa343dd7e9d9c54e3d5b723b509 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc": 0.335, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014933117490932573 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc_norm": 0.355, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.015139491543780532 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_2.json new file mode 100644 index 0000000000000000000000000000000000000000..506d8a74fb90cbe62c099f1e795e0b3fc7260321 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc": 0.28, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014205696104091512 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc_norm": 0.282, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014236526215291343 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8e1b1ce84adab77dec17abe62b15c9a0cfcf703c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc": 0.28, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014205696104091512 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc_norm": 0.293, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014399942998441275 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_4.json new file mode 100644 index 0000000000000000000000000000000000000000..974a314dff63b2f3e436d133fe3143cdafa5e18c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc": 0.308, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014606483127342761 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc_norm": 0.322, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.014782913600996662 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_5.json new file mode 100644 index 0000000000000000000000000000000000000000..f6b2b45544faa9576fe9418128f6e6b20f2db1fc --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_sciq_Multiple-Choice_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc": 0.289, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_stderr": 0.014341711358296177 + }, + { + "task_name": "sciq", + "prompt_name": "Multiple Choice", + "acc_norm": 0.292, + "dataset_path": "sciq", + "dataset_name": null, + "subset": null, + "acc_norm_stderr": 0.01438551156347735 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..fd3ff09ecd87b73a014f223fec373c09f9ae1cd5 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc": 0.48583645109567075, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011557792331301673 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc_norm": 0.48850881881346875, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011559378273599123 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..742802d4ef265846b9cd000fae8329532e049447 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc": 0.47835382148583644, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011551591851683333 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc_norm": 0.4890432923570283, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011559655791130734 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..ee0e94d3af3c92ebbbefec7c4ffe2ce7174a639c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc": 0.4767504008551577, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.01154992548392746 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc_norm": 0.47728487439871725, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011550494192008943 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..31d588f23dcae452b56ac5be2b3cf2d22319d365 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc": 0.4681988241582042, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.01153902203511123 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc_norm": 0.4836985569214324, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011556285484521566 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..2d3044e376f14e4ab27c5dd649d99300ad36d63a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc": 0.467129877071085, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011537420054210303 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc_norm": 0.4756814537680385, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.01154874830148732 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..7583c974e3739b09b5c136d48b588b6f2f6e12e0 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Answer-Given-options_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc": 0.46392303580972744, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.01153229486915312 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Answer Given options", + "acc_norm": 0.47247461250668094, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011544898473864583 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c073d0e2535b9320e31e45a9c4a066d316d9e331 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc": 0.5066809192944949, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011561400034509398 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc_norm": 0.5259219668626403, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011546883081384901 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cdeaaa80f125cbc8db5e007d9a300ce94436129a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc": 0.47835382148583644, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011551591851683333 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc_norm": 0.49438802779262425, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011561703928784335 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..d842c78136ae19221cf44e5fb5c652a8db857d71 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc": 0.4794227685729556, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011552636515221862 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc_norm": 0.4906467129877071, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011560409019420362 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..5d8ecf43557897f20fb0eaa84217824e3c1c1cec --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc": 0.4751469802244789, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.01154813982307477 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc_norm": 0.4735435595938001, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011546234813777404 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..379e6438f5b4eafffd555d077103cf78a2ecd77f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc": 0.467129877071085, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011537420054210303 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc_norm": 0.4692677712453234, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011540570846495542 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..899afec26021b54bc7401821b1003e2a0581e044 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Choose-Story-Ending_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc": 0.45911277391769106, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.01152370806018208 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Choose Story Ending", + "acc_norm": 0.46873329770176375, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011539803085637734 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c5f125083e520449afa00c033cad3f07e9d496a8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_0.json @@ -0,0 +1,15 @@ +{ + "results": [], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f814f3099551f82bccdb80fb57b28a403afe63f4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_1.json @@ -0,0 +1,15 @@ +{ + "results": [], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..ff22dcd291b12794cc589d9c6d0c9bb6838e3d1b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_2.json @@ -0,0 +1,15 @@ +{ + "results": [], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..f6d6c1d471c1aa0594927e9e8f701e4f49d6c212 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_3.json @@ -0,0 +1,15 @@ +{ + "results": [], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..1a5bd6c20f742544b90167b3615e21faeeea8bb3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_4.json @@ -0,0 +1,15 @@ +{ + "results": [], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..af9fa4d9b2f3fb7e61f26ef81071052aaf3db5b9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Generate-Ending_5.json @@ -0,0 +1,15 @@ +{ + "results": [], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.json new file mode 100644 index 0000000000000000000000000000000000000000..76b4e9d128ee78ed42682af651cf95cb061eb1cd --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc": 0.47728487439871725, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011550494192008947 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc_norm": 0.48476750400855156, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011557065368348286 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cee45a6e736cfc7a336c3fdeb2aafb2455f25d2d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc": 0.47247461250668094, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011544898473864581 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc_norm": 0.48476750400855156, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011557065368348288 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.json new file mode 100644 index 0000000000000000000000000000000000000000..63c48f916771549160eae3af59b7b2c2151162c8 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc": 0.4719401389631213, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011544210396951667 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc_norm": 0.47728487439871725, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011550494192008943 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.json new file mode 100644 index 0000000000000000000000000000000000000000..6b32f537d3612c8cf174d2a167322c42079650e1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc": 0.4692677712453234, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011540570846495544 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc_norm": 0.47728487439871725, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011550494192008941 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.json new file mode 100644 index 0000000000000000000000000000000000000000..67379b9ad4fa516305a39645e271925a025a0281 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc": 0.4660609299839658, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011535764881641411 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc_norm": 0.4708711918760021, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011542794417345717 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a0b84f145fdbb71f79436871b4cfcc71173723a2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Novel-Correct-Ending_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc": 0.4580438268305719, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011521653168224729 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Novel Correct Ending", + "acc_norm": 0.4649919828968466, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011534056494505859 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c0471aeabae0ef55194cf0a34011296066434410 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc": 0.49812934259754144, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011562351329083266 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc_norm": 0.5189738107963656, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.0115541041740197 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.json new file mode 100644 index 0000000000000000000000000000000000000000..cc62f1a43cd63a82b9dcc27d31db020711e77b0a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc": 0.4794227685729556, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011552636515221862 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc_norm": 0.48850881881346875, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011559378273599118 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.json new file mode 100644 index 0000000000000000000000000000000000000000..c8606af149bfd319c8d9f0181464ce0402f4ef58 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc": 0.4740780331373597, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011546883081384903 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc_norm": 0.4831640833778728, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011555875693960773 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.json new file mode 100644 index 0000000000000000000000000000000000000000..aa6a222c369d3a2e6bacf93be384513a27ba8571 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc": 0.467129877071085, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.0115374200542103 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc_norm": 0.4767504008551577, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011549925483927456 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.json new file mode 100644 index 0000000000000000000000000000000000000000..58f332fdc2b2c8393d8ffadc583aa8dba8fa76b4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc": 0.46392303580972744, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.01153229486915312 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc_norm": 0.47033671833244256, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011542066509767012 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.json new file mode 100644 index 0000000000000000000000000000000000000000..50f19f27cb87c6ea60c5c49adaedb6793a3c5cec --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_story_cloze_2016_Story-Continuation-and-Options_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc": 0.4537680384820951, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_stderr": 0.011512899199863038 + }, + { + "task_name": "story_cloze_2016", + "prompt_name": "Story Continuation and Options", + "acc_norm": 0.4633885622661678, + "dataset_path": "story_cloze", + "dataset_name": "2016", + "subset": null, + "acc_norm_stderr": 0.011531394084549623 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_0.json new file mode 100644 index 0000000000000000000000000000000000000000..44df4c7058b5e24dd7a5658b777e24be29b87b0f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc": 0.5342960288808665, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.03002557981936642 + }, + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc_norm": 0.4729241877256318, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030052303463143706 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_1.json new file mode 100644 index 0000000000000000000000000000000000000000..c3af59dd2bbff22fa9cf55b6afa58af927d64ff1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc": 0.4981949458483754, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030096267148976633 + }, + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc_norm": 0.5018050541516246, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030096267148976626 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_2.json new file mode 100644 index 0000000000000000000000000000000000000000..903e8043a30dd8498c95a86682982326965c4062 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc": 0.5234657039711191, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030063300411902652 + }, + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc_norm": 0.5234657039711191, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030063300411902652 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_3.json new file mode 100644 index 0000000000000000000000000000000000000000..95811cd2493a5e588e73b3514187557a0c062cd4 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030080573208738064 + }, + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc_norm": 0.49097472924187724, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030091559826331334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_4.json new file mode 100644 index 0000000000000000000000000000000000000000..0c4f090705159114d3023b289bc263a56b3f5877 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc": 0.5054151624548736, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030094698123239966 + }, + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc_norm": 0.5090252707581228, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030091559826331334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e517d29c34720cf3aa5b2960fdfa806b1df5aede --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_GPT-3-style_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc": 0.5018050541516246, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030096267148976633 + }, + { + "task_name": "superglue_rte", + "prompt_name": "GPT-3 style", + "acc_norm": 0.5054151624548736, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030094698123239966 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.json new file mode 100644 index 0000000000000000000000000000000000000000..db3e48e311aee8179b6e7cd50d57b8073658546f --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030052303463143706 + }, + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030052303463143706 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.json new file mode 100644 index 0000000000000000000000000000000000000000..8c7310ea1ba37d22b7f314a96a824705c5573ee6 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc": 0.5306859205776173, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030039730592197812 + }, + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.5415162454873647, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.029992535385373314 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.json new file mode 100644 index 0000000000000000000000000000000000000000..8073c00f11f4691b88e9987cde99b344decc5f0c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc": 0.5090252707581228, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030091559826331334 + }, + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030080573208738064 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.json new file mode 100644 index 0000000000000000000000000000000000000000..dc3376550df3d5fade7c7abfe86db48ba38e8544 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc": 0.5234657039711191, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.03006330041190266 + }, + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.51985559566787, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030072723167317177 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.json new file mode 100644 index 0000000000000000000000000000000000000000..bb4b4a2445ce89accfd7b3eb67c3d77e434c3750 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030080573208738064 + }, + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.5306859205776173, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030039730592197816 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.json new file mode 100644 index 0000000000000000000000000000000000000000..636c642df190d68eb0b4dfc5762407695c4aed35 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_MNLI-crowdsource_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030080573208738064 + }, + { + "task_name": "superglue_rte", + "prompt_name": "MNLI crowdsource", + "acc_norm": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030086851767188564 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.json new file mode 100644 index 0000000000000000000000000000000000000000..229e893ca8da8f7a9d2ec735db039bfdfc0d902a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc": 0.5054151624548736, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030094698123239966 + }, + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc_norm": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030052303463143706 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.json new file mode 100644 index 0000000000000000000000000000000000000000..f71b52fa30f5cb5dd4d7e85043feb149fbf8a3df --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc": 0.49458483754512633, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030094698123239966 + }, + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc_norm": 0.5090252707581228, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030091559826331334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f9e4ce840f63642fb533ff555a699af837499015 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc": 0.5054151624548736, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030094698123239966 + }, + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc_norm": 0.5054151624548736, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030094698123239966 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.json new file mode 100644 index 0000000000000000000000000000000000000000..a8c33338ae30783bda0319da9dff1101d642f863 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030086851767188564 + }, + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc_norm": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030080573208738064 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.json new file mode 100644 index 0000000000000000000000000000000000000000..6ba080ae305b9ecccf698955aa96610315afe2e9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc": 0.5018050541516246, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030096267148976626 + }, + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc_norm": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030086851767188564 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e1c0cdf11017c90e99ec900402dd7bb9cb3f6d33 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_does-it-follow-that_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc": 0.4981949458483754, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030096267148976633 + }, + { + "task_name": "superglue_rte", + "prompt_name": "does it follow that", + "acc_norm": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030080573208738064 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_0.json new file mode 100644 index 0000000000000000000000000000000000000000..ac8cb59d1f23cdbb19b64eca67521acea77910da --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030052303463143706 + }, + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc_norm": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030052303463143706 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_1.json new file mode 100644 index 0000000000000000000000000000000000000000..6a265a83311f9be1c3a18d2c7e8b9aeca241fee1 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc": 0.48375451263537905, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030080573208738064 + }, + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc_norm": 0.47653429602888087, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.03006330041190266 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_2.json new file mode 100644 index 0000000000000000000000000000000000000000..f6438af7483e57e375a103618f18f283b8a4bc19 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc": 0.5018050541516246, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030096267148976633 + }, + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc_norm": 0.5090252707581228, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030091559826331334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3d623d80fb4c33082b4c9a9925a07ac8a72e9619 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030080573208738064 + }, + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc_norm": 0.5234657039711191, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.03006330041190266 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_4.json new file mode 100644 index 0000000000000000000000000000000000000000..da684bcafa8e09c8fb15cb2bffac7195252749ef --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030086851767188564 + }, + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc_norm": 0.516245487364621, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030080573208738064 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_5.json new file mode 100644 index 0000000000000000000000000000000000000000..7f187c306232a1fb169d8662c764e9b502ed81ee --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_guaranteed-true_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030086851767188564 + }, + { + "task_name": "superglue_rte", + "prompt_name": "guaranteed true", + "acc_norm": 0.51985559566787, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030072723167317177 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_0.json new file mode 100644 index 0000000000000000000000000000000000000000..b7dca84465fe621a48f925b071631ac1e5041d8e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030052303463143706 + }, + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc_norm": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030052303463143706 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_1.json new file mode 100644 index 0000000000000000000000000000000000000000..fb018a4b680b76565a083f5e2bd75715f89c7e60 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc": 0.4981949458483754, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030096267148976633 + }, + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc_norm": 0.5234657039711191, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.03006330041190266 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_2.json new file mode 100644 index 0000000000000000000000000000000000000000..63a1a959d60ea426ce5d97adf941dc6d34f4ef32 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030086851767188564 + }, + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc_norm": 0.5090252707581228, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030091559826331334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_3.json new file mode 100644 index 0000000000000000000000000000000000000000..67e57cd00d645b33770d421cbc131173c8dc9a40 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc": 0.5270758122743683, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030052303463143706 + }, + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc_norm": 0.5234657039711191, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.03006330041190266 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_4.json new file mode 100644 index 0000000000000000000000000000000000000000..7e64f8fd9ecd930e425c3d36bb371a81a76c0968 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc": 0.5342960288808665, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030025579819366426 + }, + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc_norm": 0.5342960288808665, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030025579819366426 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_5.json new file mode 100644 index 0000000000000000000000000000000000000000..7a33b0a3cd74a79fe051c6a58f636621d652303a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_superglue_rte_should-assume_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc": 0.5126353790613718, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_stderr": 0.030086851767188564 + }, + { + "task_name": "superglue_rte", + "prompt_name": "should assume", + "acc_norm": 0.5054151624548736, + "dataset_path": "super_glue", + "dataset_name": "rte", + "subset": null, + "acc_norm_stderr": 0.030094698123239966 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_0.json new file mode 100644 index 0000000000000000000000000000000000000000..0ead0d863af11118ab66f54f340854ee357914d9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc": 0.4996053670086819, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052481306049512 + }, + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc_norm": 0.49329123914759276, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014051220692330346 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_1.json new file mode 100644 index 0000000000000000000000000000000000000000..44e9ec14d67142878623c9584252000f70ccd796 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc": 0.5035516969218626, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052131146915864 + }, + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc_norm": 0.5019731649565904, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052376259225632 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_2.json new file mode 100644 index 0000000000000000000000000000000000000000..aeb7fc16427237db9f985eedd6c1f2b04eb8908a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc": 0.4996053670086819, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052481306049516 + }, + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc_norm": 0.4940805051302289, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01405150083848581 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3501c5ff781f88a003e1630bed858bf883ff409c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc": 0.4956590370955012, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051956064076892 + }, + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc_norm": 0.5027624309392266, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052271211616436 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_4.json new file mode 100644 index 0000000000000000000000000000000000000000..e09d459bb0301ac807f85dccb200588f54d9b7d3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc": 0.4925019731649566, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014050905521228573 + }, + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc_norm": 0.500394632991318, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01405248130604952 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_5.json new file mode 100644 index 0000000000000000000000000000000000000000..fa4296100f4e47b086ba4891440ad7c6db9bc8c9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_Replace_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc": 0.4980268350434096, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052376259225636 + }, + { + "task_name": "winogrande", + "prompt_name": "Replace", + "acc_norm": 0.49171270718232046, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014050555322824194 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_0.json new file mode 100644 index 0000000000000000000000000000000000000000..c46f45e878a7ca17b3699a61c237e41313fc05f3 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc": 0.494869771112865, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051745961790516 + }, + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc_norm": 0.47908445146014206, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014040185494212952 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_1.json new file mode 100644 index 0000000000000000000000000000000000000000..680bc4f3c0c92589bdf3ad13192f109668c1b608 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc": 0.5011838989739542, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052446290529012 + }, + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc_norm": 0.505130228887135, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014051745961790513 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_2.json new file mode 100644 index 0000000000000000000000000000000000000000..7cc86e7525b55ea78d89c0a6241cd90752a7557a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc": 0.5098658247829518, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014049749833367596 + }, + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc_norm": 0.500394632991318, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052481306049516 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_3.json new file mode 100644 index 0000000000000000000000000000000000000000..3541546911467d2b5189800595eef8dbf656a52c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc": 0.5059194948697711, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051500838485807 + }, + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc_norm": 0.5114443567482242, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014048804199859325 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_4.json new file mode 100644 index 0000000000000000000000000000000000000000..d3da267459e4d7228537a46dca8a9f09537cfd77 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc": 0.5201262825572218, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.01404109666434433 + }, + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc_norm": 0.5288082083662194, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014029141615909617 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_5.json new file mode 100644 index 0000000000000000000000000000000000000000..e0ffe907d27d090f326b4f204a28e67a36ba25c2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_True-or-False_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc": 0.5185477505919495, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014042813708888378 + }, + { + "task_name": "winogrande", + "prompt_name": "True or False", + "acc_norm": 0.5138121546961326, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014047122916440415 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.json new file mode 100644 index 0000000000000000000000000000000000000000..81c8e469cfee7c0d6dea367d5b48765740bd0e71 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc": 0.494869771112865, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051745961790516 + }, + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc_norm": 0.4988161010260458, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052446290529024 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.json new file mode 100644 index 0000000000000000000000000000000000000000..57f5a2d673eec1211c467f47bb9947943125f21a --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc": 0.5209155485398579, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014040185494212947 + }, + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc_norm": 0.505130228887135, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014051745961790513 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.json new file mode 100644 index 0000000000000000000000000000000000000000..684ba6e321d1506b0ceb03cb6db3dd523625d43c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc": 0.49329123914759276, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051220692330349 + }, + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc_norm": 0.5074980268350434, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01405090552122858 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.json new file mode 100644 index 0000000000000000000000000000000000000000..5dbe78faa98db00c6bea61a6fcb0ec29976a935b --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc": 0.489344909234412, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.0140492945362904 + }, + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc_norm": 0.5074980268350434, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01405090552122858 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.json new file mode 100644 index 0000000000000000000000000000000000000000..562970f84bfda4118d8b29ea7ad11fc11e2c0c58 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc": 0.48303078137332284, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014044390401612976 + }, + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc_norm": 0.5082872928176796, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014050555322824189 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.json new file mode 100644 index 0000000000000000000000000000000000000000..c5e61c2d85aecc0822c38bc409039cecde1adb56 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_does-underscore-refer-to_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc": 0.5043409629044988, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051956064076892 + }, + { + "task_name": "winogrande", + "prompt_name": "does underscore refer to", + "acc_norm": 0.5090765588003157, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014050170094497704 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_0.json new file mode 100644 index 0000000000000000000000000000000000000000..0d9fdd2088247cf0d8d3a72fdd0d5006f66ab6ae --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc": 0.4940805051302289, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051500838485807 + }, + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc_norm": 0.48697711128650356, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014047718393997667 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_1.json new file mode 100644 index 0000000000000000000000000000000000000000..8fa085992248342924362a6f2ad71a0140c49021 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc": 0.5059194948697711, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051500838485807 + }, + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc_norm": 0.4988161010260458, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052446290529024 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_2.json new file mode 100644 index 0000000000000000000000000000000000000000..a29fc5a66a13524269ed3b31c3913d41b29e4ec2 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc": 0.5035516969218626, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052131146915853 + }, + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc_norm": 0.494869771112865, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01405174596179052 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_3.json new file mode 100644 index 0000000000000000000000000000000000000000..e6773d3eb6dfa3502253855084014a54defd110d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc": 0.5114443567482242, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014048804199859325 + }, + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc_norm": 0.5019731649565904, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052376259225636 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_4.json new file mode 100644 index 0000000000000000000000000000000000000000..f654974515e632819b766f6d2738da584e6c8b74 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc": 0.5059194948697711, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051500838485807 + }, + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc_norm": 0.494869771112865, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014051745961790523 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_5.json new file mode 100644 index 0000000000000000000000000000000000000000..acadd858eae3dfb960efbc2d8ba6aacef607782c --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_stand-for_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc": 0.5043409629044988, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.0140519560640769 + }, + { + "task_name": "winogrande", + "prompt_name": "stand for", + "acc_norm": 0.5074980268350434, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014050905521228573 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_0.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_0.json new file mode 100644 index 0000000000000000000000000000000000000000..d8ebde96643df7618a12da0c9834e951f6ef9b90 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_0.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc": 0.4940805051302289, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014051500838485807 + }, + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc_norm": 0.4980268350434096, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014052376259225636 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 0, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_1.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_1.json new file mode 100644 index 0000000000000000000000000000000000000000..3afae4ac995e073b6b448fbe03407e6a4b1720ca --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_1.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc": 0.4988161010260458, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052446290529015 + }, + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc_norm": 0.5059194948697711, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01405150083848581 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_2.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_2.json new file mode 100644 index 0000000000000000000000000000000000000000..27d4eef23c81b791f8680edc154f6be00132a44e --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_2.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc": 0.5130228887134964, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.01404771839399767 + }, + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc_norm": 0.5153906866614049, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014045826789783658 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_3.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_3.json new file mode 100644 index 0000000000000000000000000000000000000000..8629d864260ad245c6a805cec6ae981e8480732d --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_3.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc": 0.5035516969218626, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014052131146915867 + }, + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc_norm": 0.5043409629044988, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014051956064076906 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_4.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_4.json new file mode 100644 index 0000000000000000000000000000000000000000..a984df59098da6d1753e9cf8ad24c790b3a2d9e9 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_4.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc": 0.516179952644041, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014045126130978594 + }, + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc_norm": 0.5185477505919495, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.014042813708888378 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_5.json b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_5.json new file mode 100644 index 0000000000000000000000000000000000000000..a7fd9dd11faf0e8edef1ee9123aca2dbc4730a70 --- /dev/null +++ b/421m3b93b9/eval/slim.lm1-421m-3b9_winogrande_underscore-refer-to_5.json @@ -0,0 +1,34 @@ +{ + "results": [ + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc": 0.5146014206787688, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_stderr": 0.014046492383275837 + }, + { + "task_name": "winogrande", + "prompt_name": "underscore refer to", + "acc_norm": 0.5146014206787688, + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "subset": null, + "acc_norm_stderr": 0.01404649238327584 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..c4e2c3577d2939b5040b0a20a618de6b49da2de0 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.24089877028027756, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.017173414751925114}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0602429217462297, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019735827921315515}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.20579574680842025, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004231009457263522}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.08332916240799547, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.001981608572483273}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.025061284049701055, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0012392427803554873}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.09446011293147276, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002719209968598222}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.035500981977101324, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011410304837119155}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.05712804835016015, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0018573058569196304}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.19971177127065387, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00412609484615567}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.0795030015783028, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018371189260261022}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.05739446254568668, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018877709092159354}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.19844049378739903, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0040280689207465616}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.07959722159137221, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018589602172209136}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..5ccc5a9ec4d120541d79402ea13011262b5b3929 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.22589305455759673, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.022128853777223092}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.0636760383787805, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018928686879005686}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.21465560524545874, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0040862979469426216}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.08793106360898206, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020170291172687546}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.0258153310792851, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011485163820911801}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.0970634133804604, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002693104539795295}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.03654657792918082, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011244764654783266}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06015617783570573, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001731616385340993}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.2083047758165073, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003990654856465214}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.08375831839050411, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018498191949607773}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.060456108963209874, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017603809529685252}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.20797656697262903, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003958930203403467}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08393986102376982, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001868986328413053}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..f1580e17474612a39e6dd4de626eaf435a09f867 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.2181985666056905, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.020057209313693918}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06498481124627159, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0020011386420842}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.21746905313127401, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.003997396166419774}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.0896029418627751, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020914068869431444}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.02616994251670982, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010742808546498235}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.09723495231428274, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.002593131028157398}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.037150713540780624, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001166615613116337}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.060563699305739245, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017420728940917927}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.20946592488018603, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0038516161621525045}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.08452300013224151, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018753532326670982}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.0612612954750956, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0018101533116452646}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.20985898868661296, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003843821091775807}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08512496663982534, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019140134423509655}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..1a32496d55568a1af476b5b16d027f5a16e4bdc6 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.22014103682854522, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.014121021928418465}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.06504255044285726, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0019722007160103546}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.22244034307675453, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004053680603825578}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.08994303780320716, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020879864562887013}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.027282852020394377, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010929915411870639}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.10265169933444417, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0026895057802058435}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.03856982497679812, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001150314331373932}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.0604090808485083, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0016905160239832511}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.21490322763973269, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0038943886476283107}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.084754358743688, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018295752882874425}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06133385290849587, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017633886902745368}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.21541183054235546, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003894009874410457}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08562089619880432, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001890131351917643}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..f3c14ca9c6812ea4d6b8a0713d1947746a87aa87 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.23631462033881548, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.011861033949555396}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07029494246016092, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0023220387520143226}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.2323415800260324, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0041177097995195215}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.09357627706871754, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002188569514395813}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.028442511855222914, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011152920246172693}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.10751759051974451, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0028173173100568714}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.0398472882402638, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0012328301392539954}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06526459739737597, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0020342135281129024}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.22459002877043055, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003981727992719586}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.08823594897094617, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001939079866052584}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06660003183647675, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0021446717417380255}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.22518731383257906, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003973399020335526}, {"task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.08926504328417516, "fixed_answer_choice_list": null, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "prompt_id": "3e41305c-5461-4cf3-853d-8a6fb5747623", "prompt_jinja": "I will verbalize an abstract representation of a sentence in natural language. To do so, I will first show the representation and then the natural language. The text needs to include all of the information in the representation.\n\n{{input | join(\", \")}} {% for i in references %}\n ||| {{ i }} \n{% endfor %}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0020036440787506707}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..765590bbdbd14fb3528645d1d1f9ae98797e3b11 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.11616030773599903, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0015546529361505977}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.11527610565934898, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.001597357514956146}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.10165258316218609, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0011952174028994707}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.0057180784907079315, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00041794309835402625}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.005765421572168692, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00038779434056181975}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.004898845575284051, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002966619221851296}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.0935153333714171, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0012381935098312207}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.09261094050145993, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001249934329445903}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.08120502722510163, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0008969413184636445}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.1120628309974173, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0014880382534987544}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.11145359813031167, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.001536810848210822}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.0981439046956662, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0011437501911380108}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.3992443682229373, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.047287020128334106}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..563b93304a722147f38a46feef6c0b803342a62d --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.14078059552913869, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.00221976086349323}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.14108387680789536, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0021792516733500486}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.11976657085043808, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0015701047468628148}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.017206700804659324, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009072660363989573}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.01748322166817754, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0008775527927838353}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.013992417587043391, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006212560386692306}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.11255197090582546, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017746332238552627}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.11332799690539361, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0017501328649797046}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.09492290402083899, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0011619324172800667}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.13379225789654714, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002090431564714085}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.13407584427515148, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0020527184712752673}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.1137232930768349, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0014668316550414584}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.1042086731348286, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06309934211501203}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..a2270d97262a4b42a2770856e4b0f87e6f4491d6 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.13943663347887444, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002759398033367747}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.12171488459719305, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0023401598379623324}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.10630215556680227, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0017455850519191441}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.021516762152375038, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0011569064574850584}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.018626628994163463, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0009866192508626622}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.0152663888678567, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006717114391917106}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.1128324613424125, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0022571080068373504}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.09879699340096988, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001895417857547826}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.08522888535359799, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.001343777904096759}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.1314389457226015, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0025941289943615456}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.11440028315941474, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002182433824619521}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.09997942609483937, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0016251160389724236}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.0171377322954867, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06330593459055657}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..12ff5a67626d6bf25a1724a53de4a11de5639a84 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.05538776778864837, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0024199263328482314}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.040463970479572356, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0017468904978614624}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.03774090249537903, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0014899783290136758}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.012159469491931562, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.001109130130657678}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.007604064503883268, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.000709232179517541}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.007082079522463564, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0005647045015772988}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.04618589777477975, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0020475544128870362}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.033405645517412985, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0014455308773342055}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.03089551417227562, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0012023587454250927}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.05247623311063658, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002312076474742962}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.03814626934220766, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0016327364638861405}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.03565842587256878, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001407350331183242}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 0.046641067952019805, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.004989684029949398}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..988cb3fa9eab2f3a8ff22cd0a2227aa8fffd59f8 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1 @@ +{"results": [{"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.009643004241734029, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.001067795747454458}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.007127897333498126, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0008632643550199134}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.006399619707610977, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006644113293843788}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.0018338967833360774, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00042237587259395955}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.0016320333348783065, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.00041268562467325934}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.0013025650029460285, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0002563862430549916}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.00804055610536443, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0008904068534508633}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.006035429145555697, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.000746032460659911}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.005357579349107303, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.000556370874558084}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.009164203837451083, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0010180261305113571}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.00673793461697, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0008217005280617456}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.006037562120654035, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.000623538158911527}, {"task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 2.4149747681186975e-14, "fixed_answer_choice_list": null, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "prompt_id": "d3c5baa3-5e37-46f8-b1b2-5b834181c9da", "prompt_jinja": "{{source}}\n\nTL;DR in English: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 7.771544673673081e-14}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..450b6aebf4b7e1b1196c7ae414185e3c1a79f93a --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 5.338094307786671, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06515454379074728}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.3832370351470869, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0028537672646734343}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.30828356868209345, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0023981421310249077}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3234341671939446, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020861690070941175}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.1322519166975594, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0020673471210697885}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.1033143597339401, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0015762839528743406}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.10912506252156819, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0015649188979805092}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.28031408744446906, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0023827372553210323}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.22341530672942397, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0018913724760170302}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.2349556526401825, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016919758520874133}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.31471736117922855, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0026371468008590496}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2516001073009941, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002129236674864883}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.26457130584396993, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001925554066453436}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..29a09fa5d388bf5bf8e129bd7c4c7ce3e5f1873d --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 6.433826778019887, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.11989855255841199}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.40964251975666766, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003020666501253355}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.32550993636187, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002454287584086977}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3417387261465731, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0020852641295850015}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.15935747289756458, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.002216002997797742}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.12285687200187982, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016832806230469548}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.1293269586311722, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016060384518741578}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3082629819121513, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0026044469872173147}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.2429416126548533, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.001999293952798324}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.2553259195048568, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017365178934114242}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.34129374979854005, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002827003240120327}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2696403103767911, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002221596261685707}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2835983446920889, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019643916549154047}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..378e01d35333e9b2a68b544d35565bdc03ee859f --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 6.776186865970581, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.13027612338178787}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.4196845537832751, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003103690599933573}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.32756403865588407, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002470550715893654}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.3456994615242823, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002129929475637036}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.16860037221437157, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0022920493551559086}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.12776430984624745, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017337185030585124}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.13519893608662834, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016620017954309335}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.31893978868636, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027339081279387904}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.24605633416820383, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019988772744413854}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.2601557777272977, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017715682630751323}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3522580926887337, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.002924494913946238}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2730911788342842, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.002243047368401998}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2886177750633452, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.001994862728455483}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.json new file mode 100644 index 0000000000000000000000000000000000000000..6801f79ef153644a7e9205df707f70a77fc9c6eb --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 7.020566480045143, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.16544766699897517}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.42734318639874264, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0031410079611583997}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3256138138684991, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0024261272195232777}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.34789692990297333, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021536933378242017}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.17472955734390694, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0023256995704774726}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.1288766340258182, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0017048737353653055}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.13831401574052396, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016843272384664577}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.32821948654889516, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0027678793350505333}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.24765275348612362, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00199334227609555}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.2649003429258158, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018155355119162445}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3603897145955444, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0029768134364865496}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2727500481766423, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022167693310356867}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2919415371671272, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.002039475699813668}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.json new file mode 100644 index 0000000000000000000000000000000000000000..884bb89b992850c05959ae84fff5dd886f967469 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.json @@ -0,0 +1 @@ +{"results": [{"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "bleu": 7.200698669964753, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.1157689803255192}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_precision": 0.437624090634025, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.003179279824545049}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_recall": 0.3266498456281742, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.002387632326495796}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge1_fmeasure": 0.351839092993201, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0021041185042472927}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_precision": 0.18498740857424395, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0024137329724986238}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_recall": 0.13302832155689895, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0016887045422994222}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rouge2_fmeasure": 0.14421065405392688, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0016795602326208235}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_precision": 0.3379896246834222, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0028207051314872405}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_recall": 0.24992221126982128, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.0019824333408461196}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeL_fmeasure": 0.26952424860691127, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017948565802735905}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_precision": 0.3704391629100675, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.003031600122985278}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_recall": 0.2752536857752764, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0022186241797642462}, {"task_name": "e2e_nlg_cleaned", "prompt_name": "generate_text_restaurant", "rougeLsum_fmeasure": 0.2967312097644227, "fixed_answer_choice_list": null, "dataset_path": "e2e_nlg_cleaned", "dataset_name": null, "subset": null, "prompt_id": "1acabbc3-c9b9-4624-a684-29faeccff46f", "prompt_jinja": "Given the following data about a restaurant:\n{% for feature in meaning_representation.split(\"]\") %} {% set key = feature.split(\"[\")[0].replace(\",\",\"\") %} {% set value = feature.replace(\",\",\"\").replace(key+\"[\", '''') %}\n{% if value != \"\" %} {{key}} : {{value}} {% endif %}\n{%- endfor %}\nGenerate some text about this restaurant. ||| {{human_reference}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0020266790652191118}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..1bb575ca85fe160a444ead814afb3058b77745c8 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.12797795432085135, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0018799734016492148}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.275464064453472, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004374905613990667}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.1677852079916876, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002401055193707188}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.01847538807730778, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0008040709160638946}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.04422035563772575, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.001983493507264152}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.02535108594839243, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0010889691593612884}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0955929953532354, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0013327918913406784}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.2050102722236835, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003107575551110148}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.1247850276283268, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0016401630453164073}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.10074066506369084, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0015160268804353234}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.21713784764034982, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003596370997570011}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.13191324210334487, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019349517526529461}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.9670577750101026, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.06343752010773956}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..208a6ce7974cc4e9f1747e8d9854041869606c9c --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.11778898844617987, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0022144139950039943}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.23907298195634552, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004048679764842211}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.14909447624513877, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002414887145078445}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.017173021230648924, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0010060910053274477}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.03748973510219624, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0019753970441503117}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.022357794213862053, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0011989809991562789}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.09290134687697076, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.001697397128254027}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.18894027078924847, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002994552121485548}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.1174411125331406, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0017708916641849504}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.09282390172451079, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0017990317605616783}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.1888493213412959, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003302537683834386}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.11734985441454097, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0019496402736569917}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.8925320899438426, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07100081936293334}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..b13d56614252c3046058c790a4d804d2c840c3a1 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.11456813037350082, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.002442376937175033}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.2269616820368796, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.004121468923814175}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.1426644412249457, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002531195073188097}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.016086575983365995, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.0009462747719450403}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.0344908112771592, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0018906717459237067}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.02059246465685267, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.001119605239554556}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.090673335147814, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0018630883326917992}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.18117689060153813, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.003112673542785174}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.11310052932229092, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018680544822379343}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.09116889615912496, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0019583141790574187}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.1824163377093735, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.003409246098959164}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.11376652839167023, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00203523039109106}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.8230669109167563, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.09002487696688462}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 3, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..391e13dfa616495cb14de1784a1dbadc236a2c34 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.032209757475768014, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0021383469275840753}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.05724382228370584, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0035817300101013906}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.03759622918935962, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.002281097510653603}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.004669294656922831, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.000541161744716199}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.00971560721075693, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 0.0010968948779340219}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.005905374972717701, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0006509380146812835}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0261460746621342, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0017471095379449765}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.0464890566796421, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.002863287054009821}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.030407650809042647, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0018076386635451438}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.026440695573576204, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.001787385663477655}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.04690042140802649, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.0029681444829010263}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.030725365967093823, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.0018715881083221349}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 0.39600889649237975, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 0.07052500390758569}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 4, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..35731b2f170c1ef5d4b544017a5e86bf7aec5631 --- /dev/null +++ b/421m3b93b9/evaluation/generation/agg.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1 @@ +{"results": [{"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_precision": 0.0027536143102180836, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_precision_stderr": 0.0007603689865072987}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_recall": 0.0020160515193857454, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_recall_stderr": 0.0005433104187067704}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge1_fmeasure": 0.002284181516098342, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge1_fmeasure_stderr": 0.0006199393327918152}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_precision": 0.0002987578459276572, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_precision_stderr": 0.00013360719712119984}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_recall": 0.0001820087669144273, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_recall_stderr": 8.275145912995973e-05}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rouge2_fmeasure": 0.00022413084823988625, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rouge2_fmeasure_stderr": 0.0001007504669010411}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_precision": 0.0021915584415584414, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_precision_stderr": 0.0006004527549949232}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_recall": 0.0016304085725385989, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_recall_stderr": 0.00044096134412067295}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeL_fmeasure": 0.0018307364399560882, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeL_fmeasure_stderr": 0.0004955666724778282}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_precision": 0.002187984971003839, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_precision_stderr": 0.0005884564175013146}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_recall": 0.0016257305747216645, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_recall_stderr": 0.00043283548090773807}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "rougeLsum_fmeasure": 0.0018262136558658854, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "rougeLsum_fmeasure_stderr": 0.00048559140321195146}, {"task_name": "gem_xsum", "prompt_name": "article_DOC_summary", "bleu": 5.93673109646816e-45, "fixed_answer_choice_list": null, "dataset_path": "GEM/xsum", "dataset_name": null, "subset": "", "prompt_id": "a8d4ecfa-c944-44d5-878c-04fd5db59e64", "prompt_jinja": "Article: {{document}}\n\nSummary: ||| {{target}}", "prompt_original_task": true, "comment": "", "bleu_stderr": 3.832184291994219e-38}], "config": {"model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 5, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..206436c4aedf2d5b74e447f087fa40a7b0027a7c --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2cea0aef0da3a1afa36194f2c4b750b7f274871bfbdfed2ea8a8c6d1b047155 +size 4820291 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ff483ffe548f941dfaef41f1c1c6319c98970c49 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcc771a7272608e6af6a22a19ea28138b886e5bc2438d0ca4f11846f0ab8bf7 +size 5740359 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..19910b338f2f6981f013568821208e0007520e9d --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:277f9fb86bb23b3a0b558b9dfbfc4888fa8690dd29c3bd264458a46cdc07db5e +size 6644570 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ac7992e9f455547d786dc0597795caa7b371fd1d --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242e69c984f2c317e182fe2927032adf62f43139af22de0b278cf8879fe917f1 +size 7576799 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..98e6e40fc38340470d7f932459844b55e81ebddb --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6471d208ac070712f72a1d9e0d584027e9ee6221593a96bfccb1f2bc83ed3716 +size 8492072 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..56fae7f309d857aecf119cc48a757fb9e78a9f50 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849a571ec0649936e2a0befa503045eba32dd2a61d3aa26942eaa3381263de96 +size 13043842 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..60cad8cc50983b4b06a1a75419c22478b08b7713 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4347015b74d02873acd3381a56749c1eecfde087969b499600b1e92e80672d04 +size 18659255 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..08210dd1858cd3188b369eaeba667a01117d0b1d --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5797221d4c5267b85fc47e777618f9750a7a4fa83650eba4e4fbca64e1a3b820 +size 24115967 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..692437041cd65b115da6cf67cad0e15584cf7aa7 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2ecefe39f8ccc4c755987c608c18907e8a683f3b205d0be7c413f7433650c2 +size 29383326 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3b8316bf15d66da79c760c8416f516ac16acfa58 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d4b62a5380e044bc5c05e3317be2583ec96162181ddfdc018308d53944764a +size 34783784 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2fcbabfcd903b26ca8c072a3710b95218f844792 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385c25d9c4355f434f458b2d12300db99f5b7a867dae5f856e04ba74d1d60b6c +size 5026679 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..927766704941e310a2fd50534b0db2d7888c4c21 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8672573846a868541416e783eda20554256077687642bb9229b9b59bd5a6a3 +size 6113127 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..950e05b9dd6791a7765d2e43e06dabd82ed6d288 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f260e89c4a5590343401010c177af02395d85dd212ca6126e42fd2a22a64dbe6 +size 7193349 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..54211ef750f97ccaf735ba8337720dcacc4a0327 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9ed96d2c49d7045ea0765e765fd9bd395a65ac3c140e08eefbbcb855dddee5 +size 8267095 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c8b316568e117c07c3c28eaa9ba7c032719674ba --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559ece116f38e438c9eee501ca794b4947c5c2bffcac3f0906a4a44b1b336ed0 +size 9348658 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5d051ac7fea2913c3fea651a8c8f612288beab24 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0162511295c2f2c36ab55510fe23baae135cd8c795ea28dd0fc1b94f1a8342a +size 5066780 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e74ba0cbdfc141c7664136ec510e8c7aeb4816f7 --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9626b1646f06d4154b2ce3f13b88ca7aa83fc10216b3eabd75fdc4a4943489 +size 7339566 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..311bbb031a87ba4d654876308340d311110c92cb --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0fe03407761c38f6a8a91f0d3e30771c287c10d679f9c219ae653733ebcb573 +size 9617001 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2b1e9338d046b16c89041e6431da0010c5f35d9e --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61056cd60000c063f3d636510b674f9c6e168f3718c9c4b83cc5c1be605374e9 +size 11666365 diff --git a/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..737c8acde4b87e769233741d3b8963c9538ec97f --- /dev/null +++ b/421m3b93b9/evaluation/generation/examples.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19bf102598fa0c70f90ac5a3588c776ec48687082913eb084a10eaeb91dcafad +size 13897297 diff --git a/421m3b93b9/evaluation/generation/merged_1shots.csv b/421m3b93b9/evaluation/generation/merged_1shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..f821039d94303ebc3da6fb666830ece10c6819c9 --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_1shots.csv @@ -0,0 +1,5 @@ +dataset,prompt,metric,value +e2e_nlg_cleaned,generate_text_restaurant,rouge2_fmeasure,0.10912506252156819 +gem_xsum,article_DOC_summary,rouge2_fmeasure,0.02535108594839243 +web_nlg_en,PALM_prompt,rouge2_fmeasure,0.035500981977101324 +wiki_lingua_en,tldr_en,rouge2_fmeasure,0.004898845575284051 diff --git a/421m3b93b9/evaluation/generation/merged_1shots.json b/421m3b93b9/evaluation/generation/merged_1shots.json new file mode 100644 index 0000000000000000000000000000000000000000..b98ec89269acf518ef99b37b31a41e4cef9a80fb --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_1shots.json @@ -0,0 +1 @@ +{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.24089877028027756, "bleu_stderr": 0.017173414751925114, "rouge1_fmeasure": 0.08332916240799547, "rouge1_fmeasure_stderr": 0.001981608572483273, "rouge1_precision": 0.0602429217462297, "rouge1_precision_stderr": 0.0019735827921315515, "rouge1_recall": 0.20579574680842025, "rouge1_recall_stderr": 0.004231009457263522, "rouge2_fmeasure": 0.035500981977101324, "rouge2_fmeasure_stderr": 0.0011410304837119155, "rouge2_precision": 0.025061284049701055, "rouge2_precision_stderr": 0.0012392427803554873, "rouge2_recall": 0.09446011293147276, "rouge2_recall_stderr": 0.002719209968598222, "rougeL_fmeasure": 0.0795030015783028, "rougeL_fmeasure_stderr": 0.0018371189260261022, "rougeL_precision": 0.05712804835016015, "rougeL_precision_stderr": 0.0018573058569196304, "rougeL_recall": 0.19971177127065387, "rougeL_recall_stderr": 0.00412609484615567, "rougeLsum_fmeasure": 0.07959722159137221, "rougeLsum_fmeasure_stderr": 0.0018589602172209136, "rougeLsum_precision": 0.05739446254568668, "rougeLsum_precision_stderr": 0.0018877709092159354, "rougeLsum_recall": 0.19844049378739903, "rougeLsum_recall_stderr": 0.0040280689207465616}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 0.3992443682229373, "bleu_stderr": 0.047287020128334106, "rouge1_fmeasure": 0.10165258316218609, "rouge1_fmeasure_stderr": 0.0011952174028994707, "rouge1_precision": 0.11616030773599903, "rouge1_precision_stderr": 0.0015546529361505977, "rouge1_recall": 0.11527610565934898, "rouge1_recall_stderr": 0.001597357514956146, "rouge2_fmeasure": 0.004898845575284051, "rouge2_fmeasure_stderr": 0.0002966619221851296, "rouge2_precision": 0.0057180784907079315, "rouge2_precision_stderr": 0.00041794309835402625, "rouge2_recall": 0.005765421572168692, "rouge2_recall_stderr": 0.00038779434056181975, "rougeL_fmeasure": 0.08120502722510163, "rougeL_fmeasure_stderr": 0.0008969413184636445, "rougeL_precision": 0.0935153333714171, "rougeL_precision_stderr": 0.0012381935098312207, "rougeL_recall": 0.09261094050145993, "rougeL_recall_stderr": 0.001249934329445903, "rougeLsum_fmeasure": 0.0981439046956662, "rougeLsum_fmeasure_stderr": 0.0011437501911380108, "rougeLsum_precision": 0.1120628309974173, "rougeLsum_precision_stderr": 0.0014880382534987544, "rougeLsum_recall": 0.11145359813031167, "rougeLsum_recall_stderr": 0.001536810848210822}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 5.338094307786671, "bleu_stderr": 0.06515454379074728, "rouge1_fmeasure": 0.3234341671939446, "rouge1_fmeasure_stderr": 0.0020861690070941175, "rouge1_precision": 0.3832370351470869, "rouge1_precision_stderr": 0.0028537672646734343, "rouge1_recall": 0.30828356868209345, "rouge1_recall_stderr": 0.0023981421310249077, "rouge2_fmeasure": 0.10912506252156819, "rouge2_fmeasure_stderr": 0.0015649188979805092, "rouge2_precision": 0.1322519166975594, "rouge2_precision_stderr": 0.0020673471210697885, "rouge2_recall": 0.1033143597339401, "rouge2_recall_stderr": 0.0015762839528743406, "rougeL_fmeasure": 0.2349556526401825, "rougeL_fmeasure_stderr": 0.0016919758520874133, "rougeL_precision": 0.28031408744446906, "rougeL_precision_stderr": 0.0023827372553210323, "rougeL_recall": 0.22341530672942397, "rougeL_recall_stderr": 0.0018913724760170302, "rougeLsum_fmeasure": 0.26457130584396993, "rougeLsum_fmeasure_stderr": 0.001925554066453436, "rougeLsum_precision": 0.31471736117922855, "rougeLsum_precision_stderr": 0.0026371468008590496, "rougeLsum_recall": 0.2516001073009941, "rougeLsum_recall_stderr": 0.002129236674864883}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.9670577750101026, "bleu_stderr": 0.06343752010773956, "rouge1_fmeasure": 0.1677852079916876, "rouge1_fmeasure_stderr": 0.002401055193707188, "rouge1_precision": 0.12797795432085135, "rouge1_precision_stderr": 0.0018799734016492148, "rouge1_recall": 0.275464064453472, "rouge1_recall_stderr": 0.004374905613990667, "rouge2_fmeasure": 0.02535108594839243, "rouge2_fmeasure_stderr": 0.0010889691593612884, "rouge2_precision": 0.01847538807730778, "rouge2_precision_stderr": 0.0008040709160638946, "rouge2_recall": 0.04422035563772575, "rouge2_recall_stderr": 0.001983493507264152, "rougeL_fmeasure": 0.1247850276283268, "rougeL_fmeasure_stderr": 0.0016401630453164073, "rougeL_precision": 0.0955929953532354, "rougeL_precision_stderr": 0.0013327918913406784, "rougeL_recall": 0.2050102722236835, "rougeL_recall_stderr": 0.003107575551110148, "rougeLsum_fmeasure": 0.13191324210334487, "rougeLsum_fmeasure_stderr": 0.0019349517526529461, "rougeLsum_precision": 0.10074066506369084, "rougeLsum_precision_stderr": 0.0015160268804353234, "rougeLsum_recall": 0.21713784764034982, "rougeLsum_recall_stderr": 0.003596370997570011}}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/merged_2shots.csv b/421m3b93b9/evaluation/generation/merged_2shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..b4c18634752ee3da66dc632d25649cf206ec7421 --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_2shots.csv @@ -0,0 +1,5 @@ +dataset,prompt,metric,value +e2e_nlg_cleaned,generate_text_restaurant,rouge2_fmeasure,0.1293269586311722 +gem_xsum,article_DOC_summary,rouge2_fmeasure,0.022357794213862053 +web_nlg_en,PALM_prompt,rouge2_fmeasure,0.03654657792918082 +wiki_lingua_en,tldr_en,rouge2_fmeasure,0.013992417587043391 diff --git a/421m3b93b9/evaluation/generation/merged_2shots.json b/421m3b93b9/evaluation/generation/merged_2shots.json new file mode 100644 index 0000000000000000000000000000000000000000..3409051b456fcfe52061696dcceb72ccf6eaa3ad --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_2shots.json @@ -0,0 +1 @@ +{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.22589305455759673, "bleu_stderr": 0.022128853777223092, "rouge1_fmeasure": 0.08793106360898206, "rouge1_fmeasure_stderr": 0.0020170291172687546, "rouge1_precision": 0.0636760383787805, "rouge1_precision_stderr": 0.0018928686879005686, "rouge1_recall": 0.21465560524545874, "rouge1_recall_stderr": 0.0040862979469426216, "rouge2_fmeasure": 0.03654657792918082, "rouge2_fmeasure_stderr": 0.0011244764654783266, "rouge2_precision": 0.0258153310792851, "rouge2_precision_stderr": 0.0011485163820911801, "rouge2_recall": 0.0970634133804604, "rouge2_recall_stderr": 0.002693104539795295, "rougeL_fmeasure": 0.08375831839050411, "rougeL_fmeasure_stderr": 0.0018498191949607773, "rougeL_precision": 0.06015617783570573, "rougeL_precision_stderr": 0.001731616385340993, "rougeL_recall": 0.2083047758165073, "rougeL_recall_stderr": 0.003990654856465214, "rougeLsum_fmeasure": 0.08393986102376982, "rougeLsum_fmeasure_stderr": 0.001868986328413053, "rougeLsum_precision": 0.060456108963209874, "rougeLsum_precision_stderr": 0.0017603809529685252, "rougeLsum_recall": 0.20797656697262903, "rougeLsum_recall_stderr": 0.003958930203403467}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 1.1042086731348286, "bleu_stderr": 0.06309934211501203, "rouge1_fmeasure": 0.11976657085043808, "rouge1_fmeasure_stderr": 0.0015701047468628148, "rouge1_precision": 0.14078059552913869, "rouge1_precision_stderr": 0.00221976086349323, "rouge1_recall": 0.14108387680789536, "rouge1_recall_stderr": 0.0021792516733500486, "rouge2_fmeasure": 0.013992417587043391, "rouge2_fmeasure_stderr": 0.0006212560386692306, "rouge2_precision": 0.017206700804659324, "rouge2_precision_stderr": 0.0009072660363989573, "rouge2_recall": 0.01748322166817754, "rouge2_recall_stderr": 0.0008775527927838353, "rougeL_fmeasure": 0.09492290402083899, "rougeL_fmeasure_stderr": 0.0011619324172800667, "rougeL_precision": 0.11255197090582546, "rougeL_precision_stderr": 0.0017746332238552627, "rougeL_recall": 0.11332799690539361, "rougeL_recall_stderr": 0.0017501328649797046, "rougeLsum_fmeasure": 0.1137232930768349, "rougeLsum_fmeasure_stderr": 0.0014668316550414584, "rougeLsum_precision": 0.13379225789654714, "rougeLsum_precision_stderr": 0.002090431564714085, "rougeLsum_recall": 0.13407584427515148, "rougeLsum_recall_stderr": 0.0020527184712752673}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 6.433826778019887, "bleu_stderr": 0.11989855255841199, "rouge1_fmeasure": 0.3417387261465731, "rouge1_fmeasure_stderr": 0.0020852641295850015, "rouge1_precision": 0.40964251975666766, "rouge1_precision_stderr": 0.003020666501253355, "rouge1_recall": 0.32550993636187, "rouge1_recall_stderr": 0.002454287584086977, "rouge2_fmeasure": 0.1293269586311722, "rouge2_fmeasure_stderr": 0.0016060384518741578, "rouge2_precision": 0.15935747289756458, "rouge2_precision_stderr": 0.002216002997797742, "rouge2_recall": 0.12285687200187982, "rouge2_recall_stderr": 0.0016832806230469548, "rougeL_fmeasure": 0.2553259195048568, "rougeL_fmeasure_stderr": 0.0017365178934114242, "rougeL_precision": 0.3082629819121513, "rougeL_precision_stderr": 0.0026044469872173147, "rougeL_recall": 0.2429416126548533, "rougeL_recall_stderr": 0.001999293952798324, "rougeLsum_fmeasure": 0.2835983446920889, "rougeLsum_fmeasure_stderr": 0.0019643916549154047, "rougeLsum_precision": 0.34129374979854005, "rougeLsum_precision_stderr": 0.002827003240120327, "rougeLsum_recall": 0.2696403103767911, "rougeLsum_recall_stderr": 0.002221596261685707}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.8925320899438426, "bleu_stderr": 0.07100081936293334, "rouge1_fmeasure": 0.14909447624513877, "rouge1_fmeasure_stderr": 0.002414887145078445, "rouge1_precision": 0.11778898844617987, "rouge1_precision_stderr": 0.0022144139950039943, "rouge1_recall": 0.23907298195634552, "rouge1_recall_stderr": 0.004048679764842211, "rouge2_fmeasure": 0.022357794213862053, "rouge2_fmeasure_stderr": 0.0011989809991562789, "rouge2_precision": 0.017173021230648924, "rouge2_precision_stderr": 0.0010060910053274477, "rouge2_recall": 0.03748973510219624, "rouge2_recall_stderr": 0.0019753970441503117, "rougeL_fmeasure": 0.1174411125331406, "rougeL_fmeasure_stderr": 0.0017708916641849504, "rougeL_precision": 0.09290134687697076, "rougeL_precision_stderr": 0.001697397128254027, "rougeL_recall": 0.18894027078924847, "rougeL_recall_stderr": 0.002994552121485548, "rougeLsum_fmeasure": 0.11734985441454097, "rougeLsum_fmeasure_stderr": 0.0019496402736569917, "rougeLsum_precision": 0.09282390172451079, "rougeLsum_precision_stderr": 0.0017990317605616783, "rougeLsum_recall": 0.1888493213412959, "rougeLsum_recall_stderr": 0.003302537683834386}}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/merged_3shots.csv b/421m3b93b9/evaluation/generation/merged_3shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..752ba487885c073091f08d5c6fa5b3dc7558ef24 --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_3shots.csv @@ -0,0 +1,5 @@ +dataset,prompt,metric,value +e2e_nlg_cleaned,generate_text_restaurant,rouge2_fmeasure,0.13519893608662834 +gem_xsum,article_DOC_summary,rouge2_fmeasure,0.02059246465685267 +web_nlg_en,PALM_prompt,rouge2_fmeasure,0.037150713540780624 +wiki_lingua_en,tldr_en,rouge2_fmeasure,0.0152663888678567 diff --git a/421m3b93b9/evaluation/generation/merged_3shots.json b/421m3b93b9/evaluation/generation/merged_3shots.json new file mode 100644 index 0000000000000000000000000000000000000000..4476172dd663f2704c3d8132864aa40e547d5670 --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_3shots.json @@ -0,0 +1 @@ +{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.2181985666056905, "bleu_stderr": 0.020057209313693918, "rouge1_fmeasure": 0.0896029418627751, "rouge1_fmeasure_stderr": 0.0020914068869431444, "rouge1_precision": 0.06498481124627159, "rouge1_precision_stderr": 0.0020011386420842, "rouge1_recall": 0.21746905313127401, "rouge1_recall_stderr": 0.003997396166419774, "rouge2_fmeasure": 0.037150713540780624, "rouge2_fmeasure_stderr": 0.001166615613116337, "rouge2_precision": 0.02616994251670982, "rouge2_precision_stderr": 0.0010742808546498235, "rouge2_recall": 0.09723495231428274, "rouge2_recall_stderr": 0.002593131028157398, "rougeL_fmeasure": 0.08452300013224151, "rougeL_fmeasure_stderr": 0.0018753532326670982, "rougeL_precision": 0.060563699305739245, "rougeL_precision_stderr": 0.0017420728940917927, "rougeL_recall": 0.20946592488018603, "rougeL_recall_stderr": 0.0038516161621525045, "rougeLsum_fmeasure": 0.08512496663982534, "rougeLsum_fmeasure_stderr": 0.0019140134423509655, "rougeLsum_precision": 0.0612612954750956, "rougeLsum_precision_stderr": 0.0018101533116452646, "rougeLsum_recall": 0.20985898868661296, "rougeLsum_recall_stderr": 0.003843821091775807}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 1.0171377322954867, "bleu_stderr": 0.06330593459055657, "rouge1_fmeasure": 0.10630215556680227, "rouge1_fmeasure_stderr": 0.0017455850519191441, "rouge1_precision": 0.13943663347887444, "rouge1_precision_stderr": 0.002759398033367747, "rouge1_recall": 0.12171488459719305, "rouge1_recall_stderr": 0.0023401598379623324, "rouge2_fmeasure": 0.0152663888678567, "rouge2_fmeasure_stderr": 0.0006717114391917106, "rouge2_precision": 0.021516762152375038, "rouge2_precision_stderr": 0.0011569064574850584, "rouge2_recall": 0.018626628994163463, "rouge2_recall_stderr": 0.0009866192508626622, "rougeL_fmeasure": 0.08522888535359799, "rougeL_fmeasure_stderr": 0.001343777904096759, "rougeL_precision": 0.1128324613424125, "rougeL_precision_stderr": 0.0022571080068373504, "rougeL_recall": 0.09879699340096988, "rougeL_recall_stderr": 0.001895417857547826, "rougeLsum_fmeasure": 0.09997942609483937, "rougeLsum_fmeasure_stderr": 0.0016251160389724236, "rougeLsum_precision": 0.1314389457226015, "rougeLsum_precision_stderr": 0.0025941289943615456, "rougeLsum_recall": 0.11440028315941474, "rougeLsum_recall_stderr": 0.002182433824619521}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 6.776186865970581, "bleu_stderr": 0.13027612338178787, "rouge1_fmeasure": 0.3456994615242823, "rouge1_fmeasure_stderr": 0.002129929475637036, "rouge1_precision": 0.4196845537832751, "rouge1_precision_stderr": 0.003103690599933573, "rouge1_recall": 0.32756403865588407, "rouge1_recall_stderr": 0.002470550715893654, "rouge2_fmeasure": 0.13519893608662834, "rouge2_fmeasure_stderr": 0.0016620017954309335, "rouge2_precision": 0.16860037221437157, "rouge2_precision_stderr": 0.0022920493551559086, "rouge2_recall": 0.12776430984624745, "rouge2_recall_stderr": 0.0017337185030585124, "rougeL_fmeasure": 0.2601557777272977, "rougeL_fmeasure_stderr": 0.0017715682630751323, "rougeL_precision": 0.31893978868636, "rougeL_precision_stderr": 0.0027339081279387904, "rougeL_recall": 0.24605633416820383, "rougeL_recall_stderr": 0.0019988772744413854, "rougeLsum_fmeasure": 0.2886177750633452, "rougeLsum_fmeasure_stderr": 0.001994862728455483, "rougeLsum_precision": 0.3522580926887337, "rougeLsum_precision_stderr": 0.002924494913946238, "rougeLsum_recall": 0.2730911788342842, "rougeLsum_recall_stderr": 0.002243047368401998}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.8230669109167563, "bleu_stderr": 0.09002487696688462, "rouge1_fmeasure": 0.1426644412249457, "rouge1_fmeasure_stderr": 0.002531195073188097, "rouge1_precision": 0.11456813037350082, "rouge1_precision_stderr": 0.002442376937175033, "rouge1_recall": 0.2269616820368796, "rouge1_recall_stderr": 0.004121468923814175, "rouge2_fmeasure": 0.02059246465685267, "rouge2_fmeasure_stderr": 0.001119605239554556, "rouge2_precision": 0.016086575983365995, "rouge2_precision_stderr": 0.0009462747719450403, "rouge2_recall": 0.0344908112771592, "rouge2_recall_stderr": 0.0018906717459237067, "rougeL_fmeasure": 0.11310052932229092, "rougeL_fmeasure_stderr": 0.0018680544822379343, "rougeL_precision": 0.090673335147814, "rougeL_precision_stderr": 0.0018630883326917992, "rougeL_recall": 0.18117689060153813, "rougeL_recall_stderr": 0.003112673542785174, "rougeLsum_fmeasure": 0.11376652839167023, "rougeLsum_fmeasure_stderr": 0.00203523039109106, "rougeLsum_precision": 0.09116889615912496, "rougeLsum_precision_stderr": 0.0019583141790574187, "rougeLsum_recall": 0.1824163377093735, "rougeLsum_recall_stderr": 0.003409246098959164}}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/merged_4shots.csv b/421m3b93b9/evaluation/generation/merged_4shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..d3af42b44fedf852a544355b4e58563418572dce --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_4shots.csv @@ -0,0 +1,5 @@ +dataset,prompt,metric,value +e2e_nlg_cleaned,generate_text_restaurant,rouge2_fmeasure,0.13831401574052396 +gem_xsum,article_DOC_summary,rouge2_fmeasure,0.005905374972717701 +web_nlg_en,PALM_prompt,rouge2_fmeasure,0.03856982497679812 +wiki_lingua_en,tldr_en,rouge2_fmeasure,0.007082079522463564 diff --git a/421m3b93b9/evaluation/generation/merged_4shots.json b/421m3b93b9/evaluation/generation/merged_4shots.json new file mode 100644 index 0000000000000000000000000000000000000000..5cebc69aaafac973e2da650195d08ffc9d2904f1 --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_4shots.json @@ -0,0 +1 @@ +{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.22014103682854522, "bleu_stderr": 0.014121021928418465, "rouge1_fmeasure": 0.08994303780320716, "rouge1_fmeasure_stderr": 0.0020879864562887013, "rouge1_precision": 0.06504255044285726, "rouge1_precision_stderr": 0.0019722007160103546, "rouge1_recall": 0.22244034307675453, "rouge1_recall_stderr": 0.004053680603825578, "rouge2_fmeasure": 0.03856982497679812, "rouge2_fmeasure_stderr": 0.001150314331373932, "rouge2_precision": 0.027282852020394377, "rouge2_precision_stderr": 0.0010929915411870639, "rouge2_recall": 0.10265169933444417, "rouge2_recall_stderr": 0.0026895057802058435, "rougeL_fmeasure": 0.084754358743688, "rougeL_fmeasure_stderr": 0.0018295752882874425, "rougeL_precision": 0.0604090808485083, "rougeL_precision_stderr": 0.0016905160239832511, "rougeL_recall": 0.21490322763973269, "rougeL_recall_stderr": 0.0038943886476283107, "rougeLsum_fmeasure": 0.08562089619880432, "rougeLsum_fmeasure_stderr": 0.001890131351917643, "rougeLsum_precision": 0.06133385290849587, "rougeLsum_precision_stderr": 0.0017633886902745368, "rougeLsum_recall": 0.21541183054235546, "rougeLsum_recall_stderr": 0.003894009874410457}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 0.046641067952019805, "bleu_stderr": 0.004989684029949398, "rouge1_fmeasure": 0.03774090249537903, "rouge1_fmeasure_stderr": 0.0014899783290136758, "rouge1_precision": 0.05538776778864837, "rouge1_precision_stderr": 0.0024199263328482314, "rouge1_recall": 0.040463970479572356, "rouge1_recall_stderr": 0.0017468904978614624, "rouge2_fmeasure": 0.007082079522463564, "rouge2_fmeasure_stderr": 0.0005647045015772988, "rouge2_precision": 0.012159469491931562, "rouge2_precision_stderr": 0.001109130130657678, "rouge2_recall": 0.007604064503883268, "rouge2_recall_stderr": 0.000709232179517541, "rougeL_fmeasure": 0.03089551417227562, "rougeL_fmeasure_stderr": 0.0012023587454250927, "rougeL_precision": 0.04618589777477975, "rougeL_precision_stderr": 0.0020475544128870362, "rougeL_recall": 0.033405645517412985, "rougeL_recall_stderr": 0.0014455308773342055, "rougeLsum_fmeasure": 0.03565842587256878, "rougeLsum_fmeasure_stderr": 0.001407350331183242, "rougeLsum_precision": 0.05247623311063658, "rougeLsum_precision_stderr": 0.002312076474742962, "rougeLsum_recall": 0.03814626934220766, "rougeLsum_recall_stderr": 0.0016327364638861405}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 7.020566480045143, "bleu_stderr": 0.16544766699897517, "rouge1_fmeasure": 0.34789692990297333, "rouge1_fmeasure_stderr": 0.0021536933378242017, "rouge1_precision": 0.42734318639874264, "rouge1_precision_stderr": 0.0031410079611583997, "rouge1_recall": 0.3256138138684991, "rouge1_recall_stderr": 0.0024261272195232777, "rouge2_fmeasure": 0.13831401574052396, "rouge2_fmeasure_stderr": 0.0016843272384664577, "rouge2_precision": 0.17472955734390694, "rouge2_precision_stderr": 0.0023256995704774726, "rouge2_recall": 0.1288766340258182, "rouge2_recall_stderr": 0.0017048737353653055, "rougeL_fmeasure": 0.2649003429258158, "rougeL_fmeasure_stderr": 0.0018155355119162445, "rougeL_precision": 0.32821948654889516, "rougeL_precision_stderr": 0.0027678793350505333, "rougeL_recall": 0.24765275348612362, "rougeL_recall_stderr": 0.00199334227609555, "rougeLsum_fmeasure": 0.2919415371671272, "rougeLsum_fmeasure_stderr": 0.002039475699813668, "rougeLsum_precision": 0.3603897145955444, "rougeLsum_precision_stderr": 0.0029768134364865496, "rougeLsum_recall": 0.2727500481766423, "rougeLsum_recall_stderr": 0.0022167693310356867}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.39600889649237975, "bleu_stderr": 0.07052500390758569, "rouge1_fmeasure": 0.03759622918935962, "rouge1_fmeasure_stderr": 0.002281097510653603, "rouge1_precision": 0.032209757475768014, "rouge1_precision_stderr": 0.0021383469275840753, "rouge1_recall": 0.05724382228370584, "rouge1_recall_stderr": 0.0035817300101013906, "rouge2_fmeasure": 0.005905374972717701, "rouge2_fmeasure_stderr": 0.0006509380146812835, "rouge2_precision": 0.004669294656922831, "rouge2_precision_stderr": 0.000541161744716199, "rouge2_recall": 0.00971560721075693, "rouge2_recall_stderr": 0.0010968948779340219, "rougeL_fmeasure": 0.030407650809042647, "rougeL_fmeasure_stderr": 0.0018076386635451438, "rougeL_precision": 0.0261460746621342, "rougeL_precision_stderr": 0.0017471095379449765, "rougeL_recall": 0.0464890566796421, "rougeL_recall_stderr": 0.002863287054009821, "rougeLsum_fmeasure": 0.030725365967093823, "rougeLsum_fmeasure_stderr": 0.0018715881083221349, "rougeLsum_precision": 0.026440695573576204, "rougeLsum_precision_stderr": 0.001787385663477655, "rougeLsum_recall": 0.04690042140802649, "rougeLsum_recall_stderr": 0.0029681444829010263}}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/merged_5shots.csv b/421m3b93b9/evaluation/generation/merged_5shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..7d932e362a726b6dacc9887b6ad70c6d3a481b14 --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_5shots.csv @@ -0,0 +1,5 @@ +dataset,prompt,metric,value +e2e_nlg_cleaned,generate_text_restaurant,rouge2_fmeasure,0.14421065405392688 +gem_xsum,article_DOC_summary,rouge2_fmeasure,0.00022413084823988625 +web_nlg_en,PALM_prompt,rouge2_fmeasure,0.0398472882402638 +wiki_lingua_en,tldr_en,rouge2_fmeasure,0.0013025650029460285 diff --git a/421m3b93b9/evaluation/generation/merged_5shots.json b/421m3b93b9/evaluation/generation/merged_5shots.json new file mode 100644 index 0000000000000000000000000000000000000000..35b51612a5c1f5e42f2e66522d08cf37d2b1353c --- /dev/null +++ b/421m3b93b9/evaluation/generation/merged_5shots.json @@ -0,0 +1 @@ +{"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.23631462033881548, "bleu_stderr": 0.011861033949555396, "rouge1_fmeasure": 0.09357627706871754, "rouge1_fmeasure_stderr": 0.002188569514395813, "rouge1_precision": 0.07029494246016092, "rouge1_precision_stderr": 0.0023220387520143226, "rouge1_recall": 0.2323415800260324, "rouge1_recall_stderr": 0.0041177097995195215, "rouge2_fmeasure": 0.0398472882402638, "rouge2_fmeasure_stderr": 0.0012328301392539954, "rouge2_precision": 0.028442511855222914, "rouge2_precision_stderr": 0.0011152920246172693, "rouge2_recall": 0.10751759051974451, "rouge2_recall_stderr": 0.0028173173100568714, "rougeL_fmeasure": 0.08823594897094617, "rougeL_fmeasure_stderr": 0.001939079866052584, "rougeL_precision": 0.06526459739737597, "rougeL_precision_stderr": 0.0020342135281129024, "rougeL_recall": 0.22459002877043055, "rougeL_recall_stderr": 0.003981727992719586, "rougeLsum_fmeasure": 0.08926504328417516, "rougeLsum_fmeasure_stderr": 0.0020036440787506707, "rougeLsum_precision": 0.06660003183647675, "rougeLsum_precision_stderr": 0.0021446717417380255, "rougeLsum_recall": 0.22518731383257906, "rougeLsum_recall_stderr": 0.003973399020335526}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 2.4149747681186975e-14, "bleu_stderr": 7.771544673673081e-14, "rouge1_fmeasure": 0.006399619707610977, "rouge1_fmeasure_stderr": 0.0006644113293843788, "rouge1_precision": 0.009643004241734029, "rouge1_precision_stderr": 0.001067795747454458, "rouge1_recall": 0.007127897333498126, "rouge1_recall_stderr": 0.0008632643550199134, "rouge2_fmeasure": 0.0013025650029460285, "rouge2_fmeasure_stderr": 0.0002563862430549916, "rouge2_precision": 0.0018338967833360774, "rouge2_precision_stderr": 0.00042237587259395955, "rouge2_recall": 0.0016320333348783065, "rouge2_recall_stderr": 0.00041268562467325934, "rougeL_fmeasure": 0.005357579349107303, "rougeL_fmeasure_stderr": 0.000556370874558084, "rougeL_precision": 0.00804055610536443, "rougeL_precision_stderr": 0.0008904068534508633, "rougeL_recall": 0.006035429145555697, "rougeL_recall_stderr": 0.000746032460659911, "rougeLsum_fmeasure": 0.006037562120654035, "rougeLsum_fmeasure_stderr": 0.000623538158911527, "rougeLsum_precision": 0.009164203837451083, "rougeLsum_precision_stderr": 0.0010180261305113571, "rougeLsum_recall": 0.00673793461697, "rougeLsum_recall_stderr": 0.0008217005280617456}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 7.200698669964753, "bleu_stderr": 0.1157689803255192, "rouge1_fmeasure": 0.351839092993201, "rouge1_fmeasure_stderr": 0.0021041185042472927, "rouge1_precision": 0.437624090634025, "rouge1_precision_stderr": 0.003179279824545049, "rouge1_recall": 0.3266498456281742, "rouge1_recall_stderr": 0.002387632326495796, "rouge2_fmeasure": 0.14421065405392688, "rouge2_fmeasure_stderr": 0.0016795602326208235, "rouge2_precision": 0.18498740857424395, "rouge2_precision_stderr": 0.0024137329724986238, "rouge2_recall": 0.13302832155689895, "rouge2_recall_stderr": 0.0016887045422994222, "rougeL_fmeasure": 0.26952424860691127, "rougeL_fmeasure_stderr": 0.0017948565802735905, "rougeL_precision": 0.3379896246834222, "rougeL_precision_stderr": 0.0028207051314872405, "rougeL_recall": 0.24992221126982128, "rougeL_recall_stderr": 0.0019824333408461196, "rougeLsum_fmeasure": 0.2967312097644227, "rougeLsum_fmeasure_stderr": 0.0020266790652191118, "rougeLsum_precision": 0.3704391629100675, "rougeLsum_precision_stderr": 0.003031600122985278, "rougeLsum_recall": 0.2752536857752764, "rougeLsum_recall_stderr": 0.0022186241797642462}}, "gem_xsum": {"article_DOC_summary": {"bleu": 5.93673109646816e-45, "bleu_stderr": 3.832184291994219e-38, "rouge1_fmeasure": 0.002284181516098342, "rouge1_fmeasure_stderr": 0.0006199393327918152, "rouge1_precision": 0.0027536143102180836, "rouge1_precision_stderr": 0.0007603689865072987, "rouge1_recall": 0.0020160515193857454, "rouge1_recall_stderr": 0.0005433104187067704, "rouge2_fmeasure": 0.00022413084823988625, "rouge2_fmeasure_stderr": 0.0001007504669010411, "rouge2_precision": 0.0002987578459276572, "rouge2_precision_stderr": 0.00013360719712119984, "rouge2_recall": 0.0001820087669144273, "rouge2_recall_stderr": 8.275145912995973e-05, "rougeL_fmeasure": 0.0018307364399560882, "rougeL_fmeasure_stderr": 0.0004955666724778282, "rougeL_precision": 0.0021915584415584414, "rougeL_precision_stderr": 0.0006004527549949232, "rougeL_recall": 0.0016304085725385989, "rougeL_recall_stderr": 0.00044096134412067295, "rougeLsum_fmeasure": 0.0018262136558658854, "rougeLsum_fmeasure_stderr": 0.00048559140321195146, "rougeLsum_precision": 0.002187984971003839, "rougeLsum_precision_stderr": 0.0005884564175013146, "rougeLsum_recall": 0.0016257305747216645, "rougeLsum_recall_stderr": 0.00043283548090773807}}} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..ba1b8479b0f3f6c001628515dd80d3be2c18101f --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.24089877028027756, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.017173414751925114 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.0602429217462297, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0019735827921315515 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.20579574680842025, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004231009457263522 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.08332916240799547, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.001981608572483273 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.025061284049701055, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0012392427803554873 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.09446011293147276, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002719209968598222 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.035500981977101324, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011410304837119155 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.05712804835016015, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0018573058569196304 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.19971177127065387, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.00412609484615567 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.0795030015783028, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018371189260261022 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.05739446254568668, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0018877709092159354 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.19844049378739903, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0040280689207465616 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.07959722159137221, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0018589602172209136 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..32c6d0fe3759fdbee5d1f4aef9a5af262d69b0f0 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.22589305455759673, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.022128853777223092 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.0636760383787805, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0018928686879005686 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.21465560524545874, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0040862979469426216 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.08793106360898206, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0020170291172687546 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.0258153310792851, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011485163820911801 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.0970634133804604, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002693104539795295 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.03654657792918082, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0011244764654783266 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.06015617783570573, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.001731616385340993 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.2083047758165073, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.003990654856465214 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.08375831839050411, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018498191949607773 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.060456108963209874, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0017603809529685252 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.20797656697262903, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003958930203403467 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08393986102376982, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001868986328413053 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..76a6629c7f1b6cba0bc061c7346bd3cf465a7e4c --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.2181985666056905, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.020057209313693918 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.06498481124627159, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0020011386420842 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.21746905313127401, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.003997396166419774 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.0896029418627751, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0020914068869431444 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.02616994251670982, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0010742808546498235 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.09723495231428274, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.002593131028157398 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.037150713540780624, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001166615613116337 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.060563699305739245, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0017420728940917927 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.20946592488018603, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0038516161621525045 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.08452300013224151, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018753532326670982 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.0612612954750956, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0018101533116452646 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.20985898868661296, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003843821091775807 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08512496663982534, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019140134423509655 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..c77c850ea600eee3b31b5cd09047c7e0c7e78a1a --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.22014103682854522, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.014121021928418465 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.06504255044285726, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0019722007160103546 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.22244034307675453, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.004053680603825578 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.08994303780320716, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0020879864562887013 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.027282852020394377, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0010929915411870639 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.10265169933444417, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0026895057802058435 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.03856982497679812, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.001150314331373932 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.0604090808485083, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0016905160239832511 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.21490322763973269, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0038943886476283107 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.084754358743688, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0018295752882874425 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.06133385290849587, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0017633886902745368 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.21541183054235546, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003894009874410457 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08562089619880432, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001890131351917643 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..d00b242ecc3643f35f1837cf160402d0ce73c563 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-web_nlg_en.templates=PALM_prompt.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "bleu": 0.23631462033881548, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.011861033949555396 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_precision": 0.07029494246016092, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0023220387520143226 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_recall": 0.2323415800260324, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0041177097995195215 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge1_fmeasure": 0.09357627706871754, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.002188569514395813 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_precision": 0.028442511855222914, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011152920246172693 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_recall": 0.10751759051974451, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0028173173100568714 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rouge2_fmeasure": 0.0398472882402638, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0012328301392539954 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_precision": 0.06526459739737597, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0020342135281129024 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_recall": 0.22459002877043055, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.003981727992719586 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeL_fmeasure": 0.08823594897094617, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001939079866052584 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_precision": 0.06660003183647675, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0021446717417380255 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_recall": 0.22518731383257906, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.003973399020335526 + }, + { + "task_name": "GEM/web_nlg_en", + "prompt_name": "PALM_prompt", + "rougeLsum_fmeasure": 0.08926504328417516, + "dataset_path": "GEM/web_nlg", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0020036440787506707 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..96df6353fafcf579b8851179316efce153bda8d1 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.11616030773599903, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0015546529361505977 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.11527610565934898, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.001597357514956146 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.10165258316218609, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0011952174028994707 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.0057180784907079315, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00041794309835402625 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.005765421572168692, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00038779434056181975 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.004898845575284051, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002966619221851296 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.0935153333714171, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0012381935098312207 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.09261094050145993, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.001249934329445903 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.08120502722510163, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0008969413184636445 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.1120628309974173, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0014880382534987544 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.11145359813031167, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.001536810848210822 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.0981439046956662, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0011437501911380108 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.3992443682229373, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.047287020128334106 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..ce56ca8626d4bd1d0a07b24e077c18ac83b4533f --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.14078059552913869, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.00221976086349323 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.14108387680789536, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0021792516733500486 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.11976657085043808, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0015701047468628148 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.017206700804659324, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0009072660363989573 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.01748322166817754, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0008775527927838353 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.013992417587043391, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0006212560386692306 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.11255197090582546, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0017746332238552627 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.11332799690539361, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0017501328649797046 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.09492290402083899, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0011619324172800667 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.13379225789654714, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.002090431564714085 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.13407584427515148, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0020527184712752673 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.1137232930768349, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0014668316550414584 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 1.1042086731348286, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.06309934211501203 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..6155f9964e5a3ee13480312ff17d8a9e81d67fe1 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.13943663347887444, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.002759398033367747 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.12171488459719305, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0023401598379623324 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.10630215556680227, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0017455850519191441 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.021516762152375038, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.0011569064574850584 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.018626628994163463, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.0009866192508626622 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.0152663888678567, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0006717114391917106 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.1128324613424125, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0022571080068373504 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.09879699340096988, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.001895417857547826 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.08522888535359799, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.001343777904096759 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.1314389457226015, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0025941289943615456 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.11440028315941474, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.002182433824619521 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.09997942609483937, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0016251160389724236 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 1.0171377322954867, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.06330593459055657 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..fc1e8fa31b22bdd7931617bb567135da49e37644 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.05538776778864837, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.0024199263328482314 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.040463970479572356, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0017468904978614624 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.03774090249537903, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0014899783290136758 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.012159469491931562, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.001109130130657678 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.007604064503883268, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.000709232179517541 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.007082079522463564, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0005647045015772988 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.04618589777477975, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0020475544128870362 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.033405645517412985, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.0014455308773342055 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.03089551417227562, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.0012023587454250927 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.05247623311063658, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.002312076474742962 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.03814626934220766, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0016327364638861405 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.03565842587256878, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001407350331183242 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 0.046641067952019805, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 0.004989684029949398 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..a38ab427e9ebddd4ed8f31387457c377a2babbb3 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_precision": 0.009643004241734029, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_precision_stderr": 0.001067795747454458 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_recall": 0.007127897333498126, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_recall_stderr": 0.0008632643550199134 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge1_fmeasure": 0.006399619707610977, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge1_fmeasure_stderr": 0.0006644113293843788 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_precision": 0.0018338967833360774, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_precision_stderr": 0.00042237587259395955 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_recall": 0.0016320333348783065, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_recall_stderr": 0.00041268562467325934 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rouge2_fmeasure": 0.0013025650029460285, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rouge2_fmeasure_stderr": 0.0002563862430549916 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_precision": 0.00804055610536443, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_precision_stderr": 0.0008904068534508633 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_recall": 0.006035429145555697, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_recall_stderr": 0.000746032460659911 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeL_fmeasure": 0.005357579349107303, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeL_fmeasure_stderr": 0.000556370874558084 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_precision": 0.009164203837451083, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_precision_stderr": 0.0010180261305113571 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_recall": 0.00673793461697, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_recall_stderr": 0.0008217005280617456 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "rougeLsum_fmeasure": 0.006037562120654035, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "rougeLsum_fmeasure_stderr": 0.000623538158911527 + }, + { + "task_name": "GEM/wiki_lingua_en", + "prompt_name": "tldr_en", + "bleu": 2.4149747681186975e-14, + "dataset_path": "GEM/wiki_lingua", + "dataset_name": "en", + "subset": null, + "bleu_stderr": 7.771544673673081e-14 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..4162ddea96191026110bb52f67eb8ded29f608e7 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 5.338094307786671, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.06515454379074728 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.3832370351470869, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0028537672646734343 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.30828356868209345, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0023981421310249077 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3234341671939446, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020861690070941175 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.1322519166975594, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0020673471210697885 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.1033143597339401, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0015762839528743406 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.10912506252156819, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0015649188979805092 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.28031408744446906, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0023827372553210323 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.22341530672942397, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0018913724760170302 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.2349556526401825, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0016919758520874133 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.31471736117922855, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0026371468008590496 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2516001073009941, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002129236674864883 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.26457130584396993, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001925554066453436 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..6dec8402f2b21e7b5c21c113b7453d4fc21b34b7 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 6.433826778019887, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.11989855255841199 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.40964251975666766, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003020666501253355 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.32550993636187, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002454287584086977 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3417387261465731, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0020852641295850015 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.15935747289756458, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.002216002997797742 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.12285687200187982, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016832806230469548 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.1293269586311722, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016060384518741578 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.3082629819121513, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0026044469872173147 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.2429416126548533, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.001999293952798324 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.2553259195048568, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017365178934114242 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.34129374979854005, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002827003240120327 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2696403103767911, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002221596261685707 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2835983446920889, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0019643916549154047 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..f744ed1a676da5c86bf6bc8efbb01ad0401875a4 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 6.776186865970581, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.13027612338178787 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.4196845537832751, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003103690599933573 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.32756403865588407, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002470550715893654 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.3456994615242823, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.002129929475637036 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.16860037221437157, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0022920493551559086 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.12776430984624745, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017337185030585124 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.13519893608662834, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016620017954309335 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.31893978868636, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0027339081279387904 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.24605633416820383, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019988772744413854 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.2601557777272977, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017715682630751323 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3522580926887337, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.002924494913946238 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2730911788342842, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.002243047368401998 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2886177750633452, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.001994862728455483 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.json new file mode 100644 index 0000000000000000000000000000000000000000..d44f772e3d6701df3bbd2324d68bdaa8df4c6359 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:56.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 7.020566480045143, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.16544766699897517 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.42734318639874264, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.0031410079611583997 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.3256138138684991, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.0024261272195232777 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.34789692990297333, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021536933378242017 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.17472955734390694, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0023256995704774726 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.1288766340258182, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0017048737353653055 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.13831401574052396, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016843272384664577 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.32821948654889516, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0027678793350505333 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.24765275348612362, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.00199334227609555 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.2649003429258158, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0018155355119162445 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3603897145955444, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.0029768134364865496 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2727500481766423, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022167693310356867 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2919415371671272, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.002039475699813668 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.json new file mode 100644 index 0000000000000000000000000000000000000000..32a7105e68f8d0c3abaf022314098bf0981b72b8 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=e2e_nlg_cleaned.templates=generate_text_restaurant.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:49:35.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "bleu": 7.200698669964753, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "bleu_stderr": 0.1157689803255192 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_precision": 0.437624090634025, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_precision_stderr": 0.003179279824545049 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_recall": 0.3266498456281742, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_recall_stderr": 0.002387632326495796 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge1_fmeasure": 0.351839092993201, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge1_fmeasure_stderr": 0.0021041185042472927 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_precision": 0.18498740857424395, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_precision_stderr": 0.0024137329724986238 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_recall": 0.13302832155689895, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_recall_stderr": 0.0016887045422994222 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rouge2_fmeasure": 0.14421065405392688, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rouge2_fmeasure_stderr": 0.0016795602326208235 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_precision": 0.3379896246834222, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_precision_stderr": 0.0028207051314872405 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_recall": 0.24992221126982128, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_recall_stderr": 0.0019824333408461196 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeL_fmeasure": 0.26952424860691127, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeL_fmeasure_stderr": 0.0017948565802735905 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_precision": 0.3704391629100675, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_precision_stderr": 0.003031600122985278 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_recall": 0.2752536857752764, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_recall_stderr": 0.0022186241797642462 + }, + { + "task_name": "e2e_nlg_cleaned", + "prompt_name": "generate_text_restaurant", + "rougeLsum_fmeasure": 0.2967312097644227, + "dataset_path": "e2e_nlg_cleaned", + "dataset_name": null, + "subset": null, + "rougeLsum_fmeasure_stderr": 0.0020266790652191118 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json new file mode 100644 index 0000000000000000000000000000000000000000..7acad21752a1354bdc53d15a52f61b6ac4e9ed26 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=1.batchsize=16.seed=1234.timestamp=2023-01-22T19:19:06.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.12797795432085135, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0018799734016492148 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.275464064453472, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004374905613990667 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.1677852079916876, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002401055193707188 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.01847538807730778, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0008040709160638946 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.04422035563772575, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.001983493507264152 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.02535108594839243, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0010889691593612884 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.0955929953532354, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0013327918913406784 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.2050102722236835, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.003107575551110148 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.1247850276283268, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0016401630453164073 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.10074066506369084, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0015160268804353234 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.21713784764034982, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.003596370997570011 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.13191324210334487, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019349517526529461 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.9670577750101026, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.06343752010773956 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 1, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..0a2298c470e3c662084d5fb698b35857e55837fe --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=2.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.11778898844617987, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0022144139950039943 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.23907298195634552, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004048679764842211 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.14909447624513877, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002414887145078445 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.017173021230648924, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0010060910053274477 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.03748973510219624, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0019753970441503117 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.022357794213862053, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0011989809991562789 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.09290134687697076, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.001697397128254027 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.18894027078924847, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002994552121485548 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.1174411125331406, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0017708916641849504 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.09282390172451079, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0017990317605616783 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.1888493213412959, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.003302537683834386 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.11734985441454097, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0019496402736569917 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.8925320899438426, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.07100081936293334 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 2, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json new file mode 100644 index 0000000000000000000000000000000000000000..52f28645e227cc655f26b78e45395b631433eab1 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=3.batchsize=16.seed=1234.timestamp=2023-01-24T16:59:52.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.11456813037350082, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.002442376937175033 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.2269616820368796, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.004121468923814175 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.1426644412249457, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002531195073188097 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.016086575983365995, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.0009462747719450403 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.0344908112771592, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0018906717459237067 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.02059246465685267, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.001119605239554556 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.090673335147814, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0018630883326917992 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.18117689060153813, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.003112673542785174 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.11310052932229092, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0018680544822379343 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.09116889615912496, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0019583141790574187 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.1824163377093735, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.003409246098959164 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.11376652839167023, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.00203523039109106 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.8230669109167563, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.09002487696688462 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 3, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..57b7092fa8c39b457fd9eb645269dd40a1f2124f --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=4.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.032209757475768014, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0021383469275840753 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.05724382228370584, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0035817300101013906 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.03759622918935962, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.002281097510653603 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.004669294656922831, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.000541161744716199 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.00971560721075693, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 0.0010968948779340219 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.005905374972717701, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0006509380146812835 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.0261460746621342, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0017471095379449765 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.0464890566796421, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.002863287054009821 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.030407650809042647, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0018076386635451438 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.026440695573576204, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.001787385663477655 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.04690042140802649, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.0029681444829010263 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.030725365967093823, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.0018715881083221349 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 0.39600889649237975, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 0.07052500390758569 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 4, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json new file mode 100644 index 0000000000000000000000000000000000000000..ff2fdfc6d3d73b330ac7ce5f5ef029dfa92255d7 --- /dev/null +++ b/421m3b93b9/evaluation/generation/slim.limited=3000.model=lm1-421m-3b9.task=gem_xsum.templates=article_DOC_summary.fewshot=5.batchsize=16.seed=1234.timestamp=2023-01-24T15:52:02.json @@ -0,0 +1,133 @@ +{ + "results": [ + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_precision": 0.0027536143102180836, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_precision_stderr": 0.0007603689865072987 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_recall": 0.0020160515193857454, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_recall_stderr": 0.0005433104187067704 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge1_fmeasure": 0.002284181516098342, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge1_fmeasure_stderr": 0.0006199393327918152 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_precision": 0.0002987578459276572, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_precision_stderr": 0.00013360719712119984 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_recall": 0.0001820087669144273, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_recall_stderr": 8.275145912995973e-05 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rouge2_fmeasure": 0.00022413084823988625, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rouge2_fmeasure_stderr": 0.0001007504669010411 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_precision": 0.0021915584415584414, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_precision_stderr": 0.0006004527549949232 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_recall": 0.0016304085725385989, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_recall_stderr": 0.00044096134412067295 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeL_fmeasure": 0.0018307364399560882, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeL_fmeasure_stderr": 0.0004955666724778282 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_precision": 0.002187984971003839, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_precision_stderr": 0.0005884564175013146 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_recall": 0.0016257305747216645, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_recall_stderr": 0.00043283548090773807 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "rougeLsum_fmeasure": 0.0018262136558658854, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "rougeLsum_fmeasure_stderr": 0.00048559140321195146 + }, + { + "task_name": "gem_xsum", + "prompt_name": "article_DOC_summary", + "bleu": 5.93673109646816e-45, + "dataset_path": "GEM/xsum", + "dataset_name": null, + "subset": "", + "bleu_stderr": 3.832184291994219e-38 + } + ], + "config": { + "model": "hf-causal", + "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-421m-3b9/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", + "task_args": "", + "num_fewshot": 5, + "batch_size": 16, + "device": "cuda", + "use_cache": false, + "limit": 3000, + "bootstrap_iters": 10, + "seed": 1234 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.csv b/421m3b93b9/evaluation/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..fa01fcc72b0db1a3133b45f9aa072acea88512c5 --- /dev/null +++ b/421m3b93b9/evaluation/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.32,0.014758652303574874,0 +anli_r2,acc,0.352,0.015110404505648664,0 +anli_r3,acc,0.33916666666666667,0.013672343491681819,0 +arc_challenge,acc,0.15870307167235495,0.010677974278076938,0 +arc_challenge,acc_norm,0.2175767918088737,0.012057262020972504,0 +arc_easy,acc,0.369949494949495,0.009906656266021151,0 +arc_easy,acc_norm,0.3489057239057239,0.009780119894465762,0 +boolq,acc,0.5773700305810398,0.008639722698719024,1 +cb,acc,0.4107142857142857,0.0663363415035954,1 +cb,f1,0.28538011695906434,,1 +copa,acc,0.63,0.04852365870939099,0 +hellaswag,acc,0.26797450707030473,0.00441999074191598,0 +hellaswag,acc_norm,0.2749452300338578,0.004455741817861901,0 +piqa,acc,0.5865070729053319,0.011489895831821135,0 +piqa,acc_norm,0.5799782372143635,0.011515615810587488,0 +rte,acc,0.48375451263537905,0.030080573208738064,0 +sciq,acc,0.693,0.014593284892852625,0 +sciq,acc_norm,0.652,0.01507060460376841,0 +storycloze_2016,acc,0.5318011758417959,0.011539022035111238,0 +winogrande,acc,0.4956590370955012,0.014051956064076903,0 diff --git a/421m3b93b9/evaluation/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.json b/421m3b93b9/evaluation/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.json new file mode 100644 index 0000000000000000000000000000000000000000..c97fb5791c8a0a305812d64ba464c84456231ef2 --- /dev/null +++ b/421m3b93b9/evaluation/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.32, + "acc_stderr": 0.014758652303574874 + }, + "anli_r2": { + "acc": 0.352, + "acc_stderr": 0.015110404505648664 + }, + "anli_r3": { + "acc": 0.33916666666666667, + "acc_stderr": 0.013672343491681819 + }, + "cb": { + "acc": 0.4107142857142857, + "acc_stderr": 0.0663363415035954, + "f1": 0.28538011695906434 + }, + "copa": { + "acc": 0.63, + "acc_stderr": 0.04852365870939099 + }, + "hellaswag": { + "acc": 0.26797450707030473, + "acc_stderr": 0.00441999074191598, + "acc_norm": 0.2749452300338578, + "acc_norm_stderr": 0.004455741817861901 + }, + "rte": { + "acc": 0.48375451263537905, + "acc_stderr": 0.030080573208738064 + }, + "winogrande": { + "acc": 0.4956590370955012, + "acc_stderr": 0.014051956064076903 + }, + "storycloze_2016": { + "acc": 0.5318011758417959, + "acc_stderr": 0.011539022035111238 + }, + "boolq": { + "acc": 0.5773700305810398, + "acc_stderr": 0.008639722698719024 + }, + "arc_easy": { + "acc": 0.369949494949495, + "acc_stderr": 0.009906656266021151, + "acc_norm": 0.3489057239057239, + "acc_norm_stderr": 0.009780119894465762 + }, + "arc_challenge": { + "acc": 0.15870307167235495, + "acc_stderr": 0.010677974278076938, + "acc_norm": 0.2175767918088737, + "acc_norm_stderr": 0.012057262020972504 + }, + "sciq": { + "acc": 0.693, + "acc_stderr": 0.014593284892852625, + "acc_norm": 0.652, + "acc_norm_stderr": 0.01507060460376841 + }, + "piqa": { + "acc": 0.5865070729053319, + "acc_stderr": 0.011489895831821135, + "acc_norm": 0.5799782372143635, + "acc_norm_stderr": 0.011515615810587488 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-22-18-55-49_0shots.csv b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-22-18-55-49_0shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..daa4bdbfff53b2d9c977f5eb806150503a003307 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-22-18-55-49_0shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.333,0.014910846164229868,0 +anli_r2,acc,0.347,0.015060472031706618,0 +anli_r3,acc,0.3358333333333333,0.013639261190932882,0 +arc_challenge,acc,0.1766211604095563,0.011144042769316503,0 +arc_challenge,acc_norm,0.21843003412969283,0.012074291605700983,0 +arc_easy,acc,0.39015151515151514,0.010009118166667398,0 +arc_easy,acc_norm,0.3421717171717172,0.009735236771958759,0 +boolq,acc,0.6220183486238532,0.008480656964585243,1 +cb,acc,0.5357142857142857,0.06724777654937658,1 +cb,f1,0.36385836385836384,,1 +copa,acc,0.63,0.04852365870939098,0 +hellaswag,acc,0.2672774347739494,0.004416339450436123,0 +hellaswag,acc_norm,0.2742481577375025,0.004452228541043547,0 +piqa,acc,0.5979325353645266,0.011439867127267533,0 +piqa,acc_norm,0.5799782372143635,0.011515615810587488,0 +rte,acc,0.5415162454873647,0.029992535385373314,0 +sciq,acc,0.671,0.014865395385928364,0 +sciq,acc_norm,0.571,0.015658997547870247,0 +storycloze_2016,acc,0.5456974879743453,0.011514040245583496,0 +winogrande,acc,0.5019731649565904,0.014052376259225632,0 diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-22-18-55-49_0shots.json b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-22-18-55-49_0shots.json new file mode 100644 index 0000000000000000000000000000000000000000..9bc48de13ba79de6f726a2d4a53b2add2481e60c --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-22-18-55-49_0shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.333, + "acc_stderr": 0.014910846164229868 + }, + "anli_r2": { + "acc": 0.347, + "acc_stderr": 0.015060472031706618 + }, + "anli_r3": { + "acc": 0.3358333333333333, + "acc_stderr": 0.013639261190932882 + }, + "cb": { + "acc": 0.5357142857142857, + "acc_stderr": 0.06724777654937658, + "f1": 0.36385836385836384 + }, + "copa": { + "acc": 0.63, + "acc_stderr": 0.04852365870939098 + }, + "hellaswag": { + "acc": 0.2672774347739494, + "acc_stderr": 0.004416339450436123, + "acc_norm": 0.2742481577375025, + "acc_norm_stderr": 0.004452228541043547 + }, + "rte": { + "acc": 0.5415162454873647, + "acc_stderr": 0.029992535385373314 + }, + "winogrande": { + "acc": 0.5019731649565904, + "acc_stderr": 0.014052376259225632 + }, + "storycloze_2016": { + "acc": 0.5456974879743453, + "acc_stderr": 0.011514040245583496 + }, + "boolq": { + "acc": 0.6220183486238532, + "acc_stderr": 0.008480656964585243 + }, + "arc_easy": { + "acc": 0.39015151515151514, + "acc_stderr": 0.010009118166667398, + "acc_norm": 0.3421717171717172, + "acc_norm_stderr": 0.009735236771958759 + }, + "arc_challenge": { + "acc": 0.1766211604095563, + "acc_stderr": 0.011144042769316503, + "acc_norm": 0.21843003412969283, + "acc_norm_stderr": 0.012074291605700983 + }, + "sciq": { + "acc": 0.671, + "acc_stderr": 0.014865395385928364, + "acc_norm": 0.571, + "acc_norm_stderr": 0.015658997547870247 + }, + "piqa": { + "acc": 0.5979325353645266, + "acc_stderr": 0.011439867127267533, + "acc_norm": 0.5799782372143635, + "acc_norm_stderr": 0.011515615810587488 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-23-19-58-52_1shots.csv b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-23-19-58-52_1shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..a131a896dfe1d535fc6b5f45e4dedb1a2128ee7b --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-23-19-58-52_1shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.322,0.014782913600996676,0 +anli_r2,acc,0.318,0.0147340793093119,0 +anli_r3,acc,0.33166666666666667,0.01359683672948517,0 +arc_challenge,acc,0.17491467576791808,0.011101562501828234,0 +arc_challenge,acc_norm,0.2167235494880546,0.012040156713481192,0 +arc_easy,acc,0.37542087542087543,0.009936218527114297,0 +arc_easy,acc_norm,0.34385521885521886,0.009746660584852448,0 +boolq,acc,0.555045871559633,0.008691897543539225,1 +cb,acc,0.48214285714285715,0.06737697508644648,1 +cb,f1,0.3421052631578947,,1 +copa,acc,0.62,0.048783173121456316,0 +hellaswag,acc,0.26628161720772753,0.004411099046251009,0 +hellaswag,acc_norm,0.273451503684525,0.004448196648382999,0 +piqa,acc,0.5935799782372143,0.011459682650123577,0 +piqa,acc_norm,0.5843307943416758,0.011498699770894795,0 +rte,acc,0.5451263537906137,0.029973636495415252,0 +sciq,acc,0.676,0.014806864733738859,0 +sciq,acc_norm,0.645,0.015139491543780534,0 +storycloze_2016,acc,0.5414216996258685,0.011522687288692525,0 +winogrande,acc,0.4980268350434096,0.014052376259225636,0 diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-23-19-58-52_1shots.json b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-23-19-58-52_1shots.json new file mode 100644 index 0000000000000000000000000000000000000000..ff63d5dc2a972c8e313a23001b1e4c501c6601ab --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-23-19-58-52_1shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.322, + "acc_stderr": 0.014782913600996676 + }, + "anli_r2": { + "acc": 0.318, + "acc_stderr": 0.0147340793093119 + }, + "anli_r3": { + "acc": 0.33166666666666667, + "acc_stderr": 0.01359683672948517 + }, + "cb": { + "acc": 0.48214285714285715, + "acc_stderr": 0.06737697508644648, + "f1": 0.3421052631578947 + }, + "copa": { + "acc": 0.62, + "acc_stderr": 0.048783173121456316 + }, + "hellaswag": { + "acc": 0.26628161720772753, + "acc_stderr": 0.004411099046251009, + "acc_norm": 0.273451503684525, + "acc_norm_stderr": 0.004448196648382999 + }, + "rte": { + "acc": 0.5451263537906137, + "acc_stderr": 0.029973636495415252 + }, + "winogrande": { + "acc": 0.4980268350434096, + "acc_stderr": 0.014052376259225636 + }, + "storycloze_2016": { + "acc": 0.5414216996258685, + "acc_stderr": 0.011522687288692525 + }, + "boolq": { + "acc": 0.555045871559633, + "acc_stderr": 0.008691897543539225 + }, + "arc_easy": { + "acc": 0.37542087542087543, + "acc_stderr": 0.009936218527114297, + "acc_norm": 0.34385521885521886, + "acc_norm_stderr": 0.009746660584852448 + }, + "arc_challenge": { + "acc": 0.17491467576791808, + "acc_stderr": 0.011101562501828234, + "acc_norm": 0.2167235494880546, + "acc_norm_stderr": 0.012040156713481192 + }, + "sciq": { + "acc": 0.676, + "acc_stderr": 0.014806864733738859, + "acc_norm": 0.645, + "acc_norm_stderr": 0.015139491543780534 + }, + "piqa": { + "acc": 0.5935799782372143, + "acc_stderr": 0.011459682650123577, + "acc_norm": 0.5843307943416758, + "acc_norm_stderr": 0.011498699770894795 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.csv b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..fa01fcc72b0db1a3133b45f9aa072acea88512c5 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.32,0.014758652303574874,0 +anli_r2,acc,0.352,0.015110404505648664,0 +anli_r3,acc,0.33916666666666667,0.013672343491681819,0 +arc_challenge,acc,0.15870307167235495,0.010677974278076938,0 +arc_challenge,acc_norm,0.2175767918088737,0.012057262020972504,0 +arc_easy,acc,0.369949494949495,0.009906656266021151,0 +arc_easy,acc_norm,0.3489057239057239,0.009780119894465762,0 +boolq,acc,0.5773700305810398,0.008639722698719024,1 +cb,acc,0.4107142857142857,0.0663363415035954,1 +cb,f1,0.28538011695906434,,1 +copa,acc,0.63,0.04852365870939099,0 +hellaswag,acc,0.26797450707030473,0.00441999074191598,0 +hellaswag,acc_norm,0.2749452300338578,0.004455741817861901,0 +piqa,acc,0.5865070729053319,0.011489895831821135,0 +piqa,acc_norm,0.5799782372143635,0.011515615810587488,0 +rte,acc,0.48375451263537905,0.030080573208738064,0 +sciq,acc,0.693,0.014593284892852625,0 +sciq,acc_norm,0.652,0.01507060460376841,0 +storycloze_2016,acc,0.5318011758417959,0.011539022035111238,0 +winogrande,acc,0.4956590370955012,0.014051956064076903,0 diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.json b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.json new file mode 100644 index 0000000000000000000000000000000000000000..c97fb5791c8a0a305812d64ba464c84456231ef2 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-53-29_2shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.32, + "acc_stderr": 0.014758652303574874 + }, + "anli_r2": { + "acc": 0.352, + "acc_stderr": 0.015110404505648664 + }, + "anli_r3": { + "acc": 0.33916666666666667, + "acc_stderr": 0.013672343491681819 + }, + "cb": { + "acc": 0.4107142857142857, + "acc_stderr": 0.0663363415035954, + "f1": 0.28538011695906434 + }, + "copa": { + "acc": 0.63, + "acc_stderr": 0.04852365870939099 + }, + "hellaswag": { + "acc": 0.26797450707030473, + "acc_stderr": 0.00441999074191598, + "acc_norm": 0.2749452300338578, + "acc_norm_stderr": 0.004455741817861901 + }, + "rte": { + "acc": 0.48375451263537905, + "acc_stderr": 0.030080573208738064 + }, + "winogrande": { + "acc": 0.4956590370955012, + "acc_stderr": 0.014051956064076903 + }, + "storycloze_2016": { + "acc": 0.5318011758417959, + "acc_stderr": 0.011539022035111238 + }, + "boolq": { + "acc": 0.5773700305810398, + "acc_stderr": 0.008639722698719024 + }, + "arc_easy": { + "acc": 0.369949494949495, + "acc_stderr": 0.009906656266021151, + "acc_norm": 0.3489057239057239, + "acc_norm_stderr": 0.009780119894465762 + }, + "arc_challenge": { + "acc": 0.15870307167235495, + "acc_stderr": 0.010677974278076938, + "acc_norm": 0.2175767918088737, + "acc_norm_stderr": 0.012057262020972504 + }, + "sciq": { + "acc": 0.693, + "acc_stderr": 0.014593284892852625, + "acc_norm": 0.652, + "acc_norm_stderr": 0.01507060460376841 + }, + "piqa": { + "acc": 0.5865070729053319, + "acc_stderr": 0.011489895831821135, + "acc_norm": 0.5799782372143635, + "acc_norm_stderr": 0.011515615810587488 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_3shots.csv b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_3shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..4d5b851d62c743906aaea7c14fbf6237a95a2654 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_3shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.316,0.014709193056057137,0 +anli_r2,acc,0.353,0.015120172605483692,0 +anli_r3,acc,0.3441666666666667,0.013720551062295756,0 +arc_challenge,acc,0.1766211604095563,0.011144042769316503,0 +arc_challenge,acc_norm,0.21245733788395904,0.011953482906582954,0 +arc_easy,acc,0.37247474747474746,0.009920469215736014,0 +arc_easy,acc_norm,0.35058922558922556,0.009791003829831555,0 +boolq,acc,0.5880733944954128,0.008608316516029646,1 +cb,acc,0.44642857142857145,0.06703189227942398,1 +cb,f1,0.311624649859944,,1 +copa,acc,0.58,0.04960449637488583,0 +hellaswag,acc,0.2672774347739494,0.004416339450436123,0 +hellaswag,acc_norm,0.27723561043616807,0.004467189716140495,0 +piqa,acc,0.6017410228509249,0.01142175969778899,0 +piqa,acc_norm,0.5859630032644179,0.01149211848141758,0 +rte,acc,0.49458483754512633,0.030094698123239966,0 +sciq,acc,0.701,0.014484778521220473,0 +sciq,acc_norm,0.658,0.01500870618212173,0 +storycloze_2016,acc,0.5430251202565473,0.011519544865928068,0 +winogrande,acc,0.4964483030781373,0.01405213114691586,0 diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_3shots.json b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_3shots.json new file mode 100644 index 0000000000000000000000000000000000000000..bd6858a1a7ea3ff673c7d1b2ce0211bfb4c118b3 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_3shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.316, + "acc_stderr": 0.014709193056057137 + }, + "anli_r2": { + "acc": 0.353, + "acc_stderr": 0.015120172605483692 + }, + "anli_r3": { + "acc": 0.3441666666666667, + "acc_stderr": 0.013720551062295756 + }, + "cb": { + "acc": 0.44642857142857145, + "acc_stderr": 0.06703189227942398, + "f1": 0.311624649859944 + }, + "copa": { + "acc": 0.58, + "acc_stderr": 0.04960449637488583 + }, + "hellaswag": { + "acc": 0.2672774347739494, + "acc_stderr": 0.004416339450436123, + "acc_norm": 0.27723561043616807, + "acc_norm_stderr": 0.004467189716140495 + }, + "rte": { + "acc": 0.49458483754512633, + "acc_stderr": 0.030094698123239966 + }, + "winogrande": { + "acc": 0.4964483030781373, + "acc_stderr": 0.01405213114691586 + }, + "storycloze_2016": { + "acc": 0.5430251202565473, + "acc_stderr": 0.011519544865928068 + }, + "boolq": { + "acc": 0.5880733944954128, + "acc_stderr": 0.008608316516029646 + }, + "arc_easy": { + "acc": 0.37247474747474746, + "acc_stderr": 0.009920469215736014, + "acc_norm": 0.35058922558922556, + "acc_norm_stderr": 0.009791003829831555 + }, + "arc_challenge": { + "acc": 0.1766211604095563, + "acc_stderr": 0.011144042769316503, + "acc_norm": 0.21245733788395904, + "acc_norm_stderr": 0.011953482906582954 + }, + "sciq": { + "acc": 0.701, + "acc_stderr": 0.014484778521220473, + "acc_norm": 0.658, + "acc_norm_stderr": 0.01500870618212173 + }, + "piqa": { + "acc": 0.6017410228509249, + "acc_stderr": 0.01142175969778899, + "acc_norm": 0.5859630032644179, + "acc_norm_stderr": 0.01149211848141758 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_4shots.csv b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_4shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..d8099de266f35fa0cbfd79c89eace31b650654c1 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_4shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.33,0.014876872027456729,0 +anli_r2,acc,0.342,0.01500870618212173,0 +anli_r3,acc,0.34,0.01368049572576779,0 +arc_challenge,acc,0.1680887372013652,0.01092771504612486,0 +arc_challenge,acc_norm,0.22013651877133106,0.012108124883460981,0 +arc_easy,acc,0.3733164983164983,0.009925009142802905,0 +arc_easy,acc_norm,0.3409090909090909,0.00972657959342402,0 +boolq,acc,0.5932721712538226,0.008591549022900909,1 +cb,acc,0.39285714285714285,0.0658538889806635,1 +cb,f1,0.27393431167016075,,1 +copa,acc,0.62,0.048783173121456316,0 +hellaswag,acc,0.2674765982871938,0.004417384102398681,0 +hellaswag,acc_norm,0.27394941246763593,0.004450718673552666,0 +piqa,acc,0.5897714907508161,0.011476256036359107,0 +piqa,acc_norm,0.5859630032644179,0.011492118481417578,0 +rte,acc,0.48014440433212996,0.0300727231673172,0 +sciq,acc,0.71,0.014356395999905692,0 +sciq,acc_norm,0.668,0.014899597242811473,0 +storycloze_2016,acc,0.5408872260823089,0.011523708060182084,0 +winogrande,acc,0.510655090765588,0.014049294536290393,0 diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_4shots.json b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_4shots.json new file mode 100644 index 0000000000000000000000000000000000000000..a10c77006ad055d2bce01191a4b3f35bffb9e16b --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-13-57-05_4shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.33, + "acc_stderr": 0.014876872027456729 + }, + "anli_r2": { + "acc": 0.342, + "acc_stderr": 0.01500870618212173 + }, + "anli_r3": { + "acc": 0.34, + "acc_stderr": 0.01368049572576779 + }, + "cb": { + "acc": 0.39285714285714285, + "acc_stderr": 0.0658538889806635, + "f1": 0.27393431167016075 + }, + "copa": { + "acc": 0.62, + "acc_stderr": 0.048783173121456316 + }, + "hellaswag": { + "acc": 0.2674765982871938, + "acc_stderr": 0.004417384102398681, + "acc_norm": 0.27394941246763593, + "acc_norm_stderr": 0.004450718673552666 + }, + "rte": { + "acc": 0.48014440433212996, + "acc_stderr": 0.0300727231673172 + }, + "winogrande": { + "acc": 0.510655090765588, + "acc_stderr": 0.014049294536290393 + }, + "storycloze_2016": { + "acc": 0.5408872260823089, + "acc_stderr": 0.011523708060182084 + }, + "boolq": { + "acc": 0.5932721712538226, + "acc_stderr": 0.008591549022900909 + }, + "arc_easy": { + "acc": 0.3733164983164983, + "acc_stderr": 0.009925009142802905, + "acc_norm": 0.3409090909090909, + "acc_norm_stderr": 0.00972657959342402 + }, + "arc_challenge": { + "acc": 0.1680887372013652, + "acc_stderr": 0.01092771504612486, + "acc_norm": 0.22013651877133106, + "acc_norm_stderr": 0.012108124883460981 + }, + "sciq": { + "acc": 0.71, + "acc_stderr": 0.014356395999905692, + "acc_norm": 0.668, + "acc_norm_stderr": 0.014899597242811473 + }, + "piqa": { + "acc": 0.5897714907508161, + "acc_stderr": 0.011476256036359107, + "acc_norm": 0.5859630032644179, + "acc_norm_stderr": 0.011492118481417578 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-17-05-33_5shots.csv b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-17-05-33_5shots.csv new file mode 100644 index 0000000000000000000000000000000000000000..fa911fcaec1ce15fe444e83b4ac6f068ead1b68c --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-17-05-33_5shots.csv @@ -0,0 +1,21 @@ +task,metric,value,err,version +anli_r1,acc,0.344,0.015029633724408943,0 +anli_r2,acc,0.337,0.014955087918653614,0 +anli_r3,acc,0.3475,0.013751753243291854,0 +arc_challenge,acc,0.1697952218430034,0.010971775157784207,0 +arc_challenge,acc_norm,0.2167235494880546,0.012040156713481189,0 +arc_easy,acc,0.38047138047138046,0.009962305992058575,0 +arc_easy,acc_norm,0.3547979797979798,0.009817629113069697,0 +boolq,acc,0.5840978593272171,0.008620469604001027,1 +cb,acc,0.44642857142857145,0.06703189227942398,1 +cb,f1,0.31143722338690893,,1 +copa,acc,0.59,0.04943110704237102,0 +hellaswag,acc,0.26857199761003786,0.004423109313298973,0 +hellaswag,acc_norm,0.27524397530372435,0.004457243336616501,0 +piqa,acc,0.5897714907508161,0.011476256036359107,0 +piqa,acc_norm,0.5799782372143635,0.011515615810587486,0 +rte,acc,0.5523465703971119,0.029931070362939526,0 +sciq,acc,0.705,0.014428554438445514,0 +sciq,acc_norm,0.682,0.014734079309311901,0 +storycloze_2016,acc,0.5424906467129877,0.01152060569518407,0 +winogrande,acc,0.516179952644041,0.014045126130978601,0 diff --git a/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-17-05-33_5shots.json b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-17-05-33_5shots.json new file mode 100644 index 0000000000000000000000000000000000000000..b19b04bfc59498f2e173d0f29f85fb5644619752 --- /dev/null +++ b/421m3b93b9/evaluation/rankeval/lm1-421m-3b9-results_lm-eval_global_step7508_2023-01-24-17-05-33_5shots.json @@ -0,0 +1,87 @@ +{ + "results": { + "anli_r1": { + "acc": 0.344, + "acc_stderr": 0.015029633724408943 + }, + "anli_r2": { + "acc": 0.337, + "acc_stderr": 0.014955087918653614 + }, + "anli_r3": { + "acc": 0.3475, + "acc_stderr": 0.013751753243291854 + }, + "cb": { + "acc": 0.44642857142857145, + "acc_stderr": 0.06703189227942398, + "f1": 0.31143722338690893 + }, + "copa": { + "acc": 0.59, + "acc_stderr": 0.04943110704237102 + }, + "hellaswag": { + "acc": 0.26857199761003786, + "acc_stderr": 0.004423109313298973, + "acc_norm": 0.27524397530372435, + "acc_norm_stderr": 0.004457243336616501 + }, + "rte": { + "acc": 0.5523465703971119, + "acc_stderr": 0.029931070362939526 + }, + "winogrande": { + "acc": 0.516179952644041, + "acc_stderr": 0.014045126130978601 + }, + "storycloze_2016": { + "acc": 0.5424906467129877, + "acc_stderr": 0.01152060569518407 + }, + "boolq": { + "acc": 0.5840978593272171, + "acc_stderr": 0.008620469604001027 + }, + "arc_easy": { + "acc": 0.38047138047138046, + "acc_stderr": 0.009962305992058575, + "acc_norm": 0.3547979797979798, + "acc_norm_stderr": 0.009817629113069697 + }, + "arc_challenge": { + "acc": 0.1697952218430034, + "acc_stderr": 0.010971775157784207, + "acc_norm": 0.2167235494880546, + "acc_norm_stderr": 0.012040156713481189 + }, + "sciq": { + "acc": 0.705, + "acc_stderr": 0.014428554438445514, + "acc_norm": 0.682, + "acc_norm_stderr": 0.014734079309311901 + }, + "piqa": { + "acc": 0.5897714907508161, + "acc_stderr": 0.011476256036359107, + "acc_norm": 0.5799782372143635, + "acc_norm_stderr": 0.011515615810587486 + } + }, + "versions": { + "anli_r1": 0, + "anli_r2": 0, + "anli_r3": 0, + "cb": 1, + "copa": 0, + "hellaswag": 0, + "rte": 0, + "winogrande": 0, + "storycloze_2016": 0, + "boolq": 1, + "arc_easy": 0, + "arc_challenge": 0, + "sciq": 0, + "piqa": 0 + } +} \ No newline at end of file diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9684999870da11bb204414e1aa4363ec0d69ce00 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddeedf8271e9b4243edc6384f2052c1b0bcb65cd4d598ebaa9473714125488a9 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50517ee30aa0e9aa443c497ea8055ac1767b6bec --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a9f29724f6eeb3f8aff929d6185370cbce35fbc926581ba1ec53afe9e85da2 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b7e1d7662b9dc6dea45d807b73dacb3135effaf1 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db68521322c838cc5f4ccd4688feec7c92c0bb633d671e1007dd867bed03212b +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..063a2695bf3a3b4003d634142abb8142a1a5a0fd --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b0c3273c735e0923cef471cbcd756eb315dcdd15f9aa685d4b16a8ca20f7a9 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb2e7b963bb146dd01a70266a698f0e86be399ce --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e4352d97a7c63954a9affa385bc15e5e59499eda9f4faf5952f29cc2637641 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e1be399f8240faa17ecb02b19dd9d72773cb77c --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0faac5c87316f90203d83fff628f09ed88eb5cc1446719275306980c2acdd04 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3aab4447fca8714bafdd83241109c896abbdcf0b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b059c844139c1618a5157754a66b4b0e6d0f287187a7dc9b8eb6a1397ba0a3e +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db2d6f3a8d1f120a8e4db917acb0775bad332062 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1906700ce1c40468a2b521f95ecabe6968e01b45fe158273cd55930e921c3d4f +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3949ca182837888adf2fe156164afc76db0f93bf --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679b423c9c619f7b885f0476f27e92dd7722358fb0c83279772721c4d1333aeb +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdbb29f2c0f7f5d743a6f0cab2fd738c8a3e28af --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6fa2159494384256664428a649306a484646e4efa41cd7b3adb0d73eefd04e1 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd8cb287d7e95ea0e5b364146b738209e96426c6 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9658541cd358a0444ecafc76fde46d31eeabd750050248f8f5d7172cf36097d +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eaf013c73520a8d5b0d84794c5835494475d5e18 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6406b6faff37daef98d83278c5665f7f7f9521472fb25d40dbd129c92130b3 +size 78980951 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..697d4f18eceb3fad420098833536fb56cde27e00 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d461ac77f6024b28748e7f2365a95690b06fcafae1066379711521132f09a7 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7503c3aee1cef369e63eb988377970b8b551b59d --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ead8f39c7de8254cb73bb94b761fc342148212a38252d880ea2c4e8a457ac6 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f0871785fa2b60c61e8785479b685741df83dee8 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f84143198790d460fe61e8465aa60cd5e1af87e6ec375a9ecf65fb454a698f0 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bfa0ca84f6c84cf507e1b769b56b8f357619928b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d88090500eb0e060f3fd21815e49a4c76d5804db0ef5c73b23349ce1d979e5 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebf9e1938b58c6cea924891c1f63bfb48229fc55 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbec5338e2dec8b5d646c2bd6e85b06526c1217352edaa7e9df5f0b5519b3864 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..79b465d89c6c05fca6343e9e17fe1d657f584b95 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64d014f515ad1493ab60aa64697706e1479ac655f7c8897bdcc8fcb241d6144 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..794cdf2f5dbbb3d161f596e71f3684c83912212d --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbcf81358c5de4a72ade2d829baabe70d4f10a8f5efa62488dd13cd85235468 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..57cc56455e4dac98ae9f10ed584b3f5f0b97fdc4 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc4070dbc0f0dfddb9aad9baebc8d06a75037e899bdb3c3efc3691c6768e456 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..513012850de0f4ac8784055d7ae83e5d9e78c566 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf1d8bb2afddb0ee7bdf8946ff2045f3157fe1affbc9ed02ab1f5577f918fd3 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d85c2ca08d9d6e0fbd4b74c07ba230292e1f3bbc --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:710facbe13ada839f2a04c18f65dfa2fa6ebac413cdca1d2f37a520ee54bd1c9 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..03346c6e74cc32851622bfe8a2c8e1059c72b142 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9941ffc369dad67e2702381ae102c0851987c69a49faf50605f352022b18373 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6cc949e3f702b53308b69a608d2eb01be083786 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab15f0d81bb130f93098e82edc8dad9bcaa57ed8c665a886886b044a2e983714 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0499b5f41a0ce84bd4492555380528294f8f4ce --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a255f510831c22b83ce817b3b42ac6be110e3902dccbc3e53402f3631b69de +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e4c92bfe1e21b32d15532e5e9a31c6cf8e53d2c --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c62847bf145de8ac3d2553336fc9f9118458cf9e77b41d68f39075bb51468f +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4121ded2af35677b4ed50d8a54073667deb8fdcc --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7053ce26910ab4d6b735368304c2ca2ec4698975948aecf44664aa35373ac9d +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcb42e979fd0a04200d996f20a9cb25543db9183 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872c6b89ae43cb280fd9f05295f03f457e94053e9cf7b32e2a649c481b1116d6 +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..152ad03597ef7a0254a7cfb57541748c445a79bd --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7620f2427f9045d1450d20ed5f4c529beb3c0df9108141ed0517d1e5abc7cda9 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60b47372a90649f568b0eed08e7e61c09166c11c --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7de80324569197e0cc75b51886134d5f345ac3f228f5941eaa2c774879dd2b1 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a3d342be2ecbcb4cd34c0c542e9125bb9ac38f9 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c92d46ee6d7f258aa2a19bd73adeaea871edb416de730ce312dc0221e85888 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..142940500ae37f8753af8d369190906ee5e14493 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3bc27e40a674149862277f5398d76ae07ba7de7006d69cf31a61cd9b41eae5 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..77114defec34b0d0e69dc904a784e119ee5dab71 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f3e057947136fddfeb1722b8ef5f2199ac939aeff7b8d64d12b5aa680aba3a +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75b5a8554ed7b7346076b298c8d00f13599f5bc2 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:908c07b2b215df68af2beb08169c38d6a7c8bd22508a24c8b1a47609fc487481 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93bb15f575a9abe082c802817af9d856c1300a5a --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa15e30a14148069ab1e29ba459164490b2ac6e8b9d2908c12fb7d6abdee469b +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..68b1ab0d4bd3dac2a80475eb2659a36477f55b3f --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c995eef19aac37f641930916c641b9814f12b55beb5f2a13cc23ea70d18e446d +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..97d22fe71329fb9777fb7017a7229793402e3df2 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c46ca81575e8fdf9fe36c106b6d5dffafa0de5a8433efb32c4a051dd134a4f1 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf723d5776d61a2ffc779778a9d32a119bfd9b31 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574e3a7a8165ba9fb5d99f33f0db2da3fcfa8f087f6485b294d284af69d5a173 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..79b956ee4a81ac4c08617fa162fc5ef4feca51af --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d37554012cc1c4322a58672019bf61584134c1f27401a76fb2db44bfc6e1d8e +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1362f1b388ebbdeacf4a91070b99eb76b4beba8b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a276d06dbbaed89dec3ad9ac06be25cfcbbb327fc4799408d02dfaf144798e1e +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..01729f83a8a89859c0164bfba1dc4d95ac53a3ed --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523bd0620ce3302daa9903963d87c7d65db5417b899a11ccb65e3020e5063423 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80d59196374d7aa8272cdc664490f1f8d5940d73 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5eba79a06ac402451aaf9a69ad77614488c734db144d3ecbba50e0aa4783874 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee278048ce24d8e8e680c8aa41fdb1da55310016 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18a4de65eb43e86817d9e04f6021f7acde371999b947d3c3f4683cdbb9954ac +size 78980770 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a2920c59024e047ca73fb4ed0178b5d056da1ba --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01169fb4f2ba1427fc7584031582f11e0b459c7e7dccf90a2e268f7726c14122 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..59a2df628ed60fa85cf3423ef100f3d60d376784 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e9543d305db2e21d415a92f1adb0896c2f5136df7c52995a5609ae1d19f6c2 +size 78980951 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..160b35bb6625aedcb4e5249f293b007af7bbccee --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5f0e689293df0272ada4c6b97e0fd51abeed971752094edcd9048f4bb4a2668 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0be8ea29a19e3a46ca6ba3b7599ed43b2fdd2828 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259dbab8de6a8d5a01977f62b7a98542d98b9dfd6e7910a1ba78062fd13c97da +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec44220afdabcc6e5e7c0b4f3394ffbc23b70382 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65fea67d6a8670616999ee78233fa8e4918e1add6bbbe5587701d9ef3f5f163f +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..569bb5f19fcfed60d899e505de31f86806c4d5e2 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71253792af2c2815ec4f96933a9b4ae0ab496e471aa73b6b08b538319ae8c39 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f4dc7e8d581a3aeb3e168f930a752baabee9d21 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704cf63d43a204add8c616cf0678d0c5199b0e627c66cc12dea9604dfe52d412 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bfd76a5dedf9e5f8caadead5edd2a80ad6a72f53 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1beebb9bf5c12c909c21de058c8d32c38ec276b55991197c8ea72ee9c9519c08 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93c228897f09e4cbd17163b52a24ddbe3f907285 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302f637284837a74ddaacedc8b8fcecfb2b5494765beaf264f3281f7d8509f74 +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab944f72e11b941b46467868972a1ef668a81bb1 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b2d55b7cdaee10fea0232bc4939f7c6c33c4644c485ab773d0312bad3ba069 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f70184c46feba976da08aad1ed43b0f8cd53207 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4e7e608692bbb4024e40059b18f99a0e6c18e0f3658cede421b0e7682a98298 +size 78981026 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2564cd7b761514b309bcf354032cd0eb999615f6 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7e07f20070cbc76b31a7adc44a9a30a96b0acbb5c56cba151f7cfe3414ff4d +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe12afde8938020c7368ffcbb4e7f942020989bc --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8074635c37d22381180d73ecdb0f3994a574dee182f276d07d13361e15e319d4 +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7c96051eae769754d3019a0205052f761e176dc --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe2d9f306221670d7b1dce81a7d1719f8bff38d04f5d4bd8fcc18464428de254 +size 78980962 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66dcedf8b39cafc7796e74c7b6458f8dfa51a034 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3aad8cae810455ee6daad8ea68a32bfac89480a975595de086a1e9c710576df +size 78981090 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c493361a92404f14425252c720ee7006f686146 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a418edc05a163c71aedb5d638b0bc8be411f1ac76406b79780a7dfa0f6a3b6d +size 78980834 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a27401ed0da69ece5565de2fb141ae26879e17d --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac0611fa8aefc608fbfceb66e0db0491431950daba8f6ce3418a19644368ee3 +size 78980898 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..972bdbea25e38478cffaec4bb0c1f77a93962695 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad8995fc5b2cfa335c198ff4823f18c69c1b0ae48dae21dd08e8ab05016e924 +size 78980823 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35d863435e219bae43b6ef0122c3fdfc20c8d36f --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9851ed60f2e73ddee0b6b7a6ccd7a6caf9f280ac1e4e514b7493069faf402fff +size 78980887 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5307a2eee344b9379b6e0be6a48bf2429cd80c7b --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e559cbf2150496b771805000b5daf850941c77060d7d5bc0aa86e77b416b02 +size 78980951 diff --git a/421m3b93b9/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/421m3b93b9/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60fa9fc7ab188ddd528c0126ef53443f4f2d6c43 --- /dev/null +++ b/421m3b93b9/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f323d5a75e3bff56a587c49e83a1b7850e7372c3db0473aa367db87ae77c44 +size 78980887 diff --git a/421m3b93b9/global_step7508/layer_01-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0dbd430a259f3ea6b9f6591213e6cfc33662148 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fe3844e89537920d555bc4bedb1a47eae24e93f343dc8302378a2677a1154c +size 134022403 diff --git a/421m3b93b9/global_step7508/layer_03-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e5e2d85315dff13343884fc44bc9c3308e94bbc --- /dev/null +++ b/421m3b93b9/global_step7508/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119dc1fb8ecd129d4b488d25a5217c0d3a7874351343e84fc5c4944ec4f44de2 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_04-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a675e6c0ac42aedf0e778cf9d6288a50ced78d9 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d43f8595c58b9f67c85eb6eff74df562295f00898fe000aa793525ff7c5227 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_05-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..efb6e67adab4cf150f00bc2df04b05f02f50fecb --- /dev/null +++ b/421m3b93b9/global_step7508/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cec0a89d32265151e9960119b51e71f69cd66930581a5af3482f3a6868478bf +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_06-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88861b825da7ace1a2bf7c4b374d26c2d3e4e2ca --- /dev/null +++ b/421m3b93b9/global_step7508/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aa1f085aa95eb3462cc8d22fdb1431acf5309df4ff6a7976a25544e0405392d +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_07-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d39e5b07a50fa0c1aa9584c7bd623ed261526765 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3abf59d1d2dd1fc34bd09dd50faab0106ea877dcb9f40d142d1179eceeda5f +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_08-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a111fbd5c30911f05f55254bc1a3ae23ad6ac12 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e4f912155c77f2998e7af3138a597eb714d1501c540ecbd224a59904354bd6 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_09-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b3cac7c8027e3608c2e50f7c1e87a15723dc612 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aec3087c50666fffd50340a0d35f8750fd92da0181d2084dc4a7aa8e7150f39 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_10-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..adab04af01b9aa512d5ce161afffc5fc6dda5889 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f161cb92464222d1523eab04439069d5d8a92760da8a17666d9f0da07f906e +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_11-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ae6f7fb333d52709a01e1cdd897c47e695f4b48 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be479858ca05f1757257a443f43bd2c70c20509efc7359bf06b2afc77914cd5 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_12-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1a564afe523fb114bc66179f675f2fef51d3afc --- /dev/null +++ b/421m3b93b9/global_step7508/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da15c2466e06eb84780b8ae3933804fd2c66fc42436776a71e2a6efc2e2c93fa +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_13-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_13-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bab6bcd879325a25320174c920f6c7a4adcf38f5 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_13-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e24bb2e919b21ddc7dfb678f0df43edbb0b3a5e366106a37af5283097944723 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_14-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6445e90cdac8c82ad6134b894322def42da58163 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582a605485bd24e8de39e9f2eeb63b66b5787c7bbadd731134e4c2e5c10b9161 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_15-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_15-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2b90e99684d96f9884858fd593793424b934346 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_15-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd6cda647755d9c51649c37cbc988a4974c016fd42774673b6ec2f52b235cac +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_16-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_16-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ccfba59df4a0e1195a299ee19ff61193d94f060f --- /dev/null +++ b/421m3b93b9/global_step7508/layer_16-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14171c50c69b281047fc5a4cd0d78cfc13a2eda4132af530b758d32787cb5730 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_17-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_17-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c14bf8344f2891291c1171d25be1ce6c312c181 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_17-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474de1a86e65cd1006d0d09e02741bbeca72cb329918e52e87c5b71cdb9d057f +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_18-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_18-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9da704e0759130dbfa587a8c2c8ecdb8fabf9cc --- /dev/null +++ b/421m3b93b9/global_step7508/layer_18-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22d924fb6f5302c0f8c3fa392ad27da0f3201207b8998fe92787287c6c85cfd +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_19-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_19-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ebe740d9fe7110252bb532532263e2ee85916a4 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_19-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7512475c95d7ed6c6f537e19768ff5319216333bb21892e82e27feb319e828 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_20-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_20-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4daf1c450edadab6f51726b413a7edc3e1fe74a --- /dev/null +++ b/421m3b93b9/global_step7508/layer_20-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8c9f9f711fdf03e50e05760ac1e5d36bef648522c0df10ea8228c233779f08 +size 39359235 diff --git a/421m3b93b9/global_step7508/layer_22-model_00-model_states.pt b/421m3b93b9/global_step7508/layer_22-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..20333f08b01124bcfcf78e32c0517fe628eda1d3 --- /dev/null +++ b/421m3b93b9/global_step7508/layer_22-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:706c529c2d8da41d0d9aa12eb7a0abe99642060319173aa0bad780a434438ed9 +size 6339 diff --git a/421m3b93b9/global_step7508/mp_rank_00_model_states.pt b/421m3b93b9/global_step7508/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22bf75e6982928815dfd12cba9624559a49fcc59 --- /dev/null +++ b/421m3b93b9/global_step7508/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d05fdd4919a55b1398dbc5e6ab6dc78718e75b8a4a3cb2a2d6bafb4a4d2a9a +size 37427 diff --git a/421m3b93b9/logs/2072596.err b/421m3b93b9/logs/2072596.err new file mode 100644 index 0000000000000000000000000000000000000000..6ec4c5e62d084d04b31bfc24f541591e3c6f4355 --- /dev/null +++ b/421m3b93b9/logs/2072596.err @@ -0,0 +1,484 @@ +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +7: Successfully preprocessed all matching files. +3: Successfully preprocessed all matching files. +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +7: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +7: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +2: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +2: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +3: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +3: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +5: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +5: warnings.warn( +6: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +6: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +4: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +4: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +3: Building extension module utils... +3: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +3: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: +4: +4: +4: +4: +4: +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: +5: +5: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: +6: +6: +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +7: Loading extension module utils... +0: Loading extension module utils... +2: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Loading extension module utils...Loading extension module utils... +0: +0: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +2: Loading extension module utils... +3: Loading extension module utils...Loading extension module utils... +3: +3: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... +3: +3: +3: +3: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +7: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +7: Loading extension module utils... +0: Loading extension module utils... +4: Loading extension module utils... +0: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +4: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +6: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +5: Loading extension module utils... +0: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +6: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +3: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +3: No modifications detected for re-loaded extension module utils, skipping build step... +3: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +7: No modifications detected for re-loaded extension module utils, skipping build step... +7: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +2: +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +2: +2: Loading extension module utils... +2: No modifications detected for re-loaded extension module utils, skipping build step... +2: Loading extension module utils... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: +4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +4: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +4: +4: Loading extension module utils...Loading extension module utils... +4: +4: No modifications detected for re-loaded extension module utils, skipping build step... +4: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +5: +5: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +5: No modifications detected for re-loaded extension module utils, skipping build step... +5: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +6: No modifications detected for re-loaded extension module utils, skipping build step... +6: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/421m3b93b9/logs/2072596.out b/421m3b93b9/logs/2072596.out new file mode 100644 index 0000000000000000000000000000000000000000..989ad9caa63418fa90453740d0e35d2f46f16a6c --- /dev/null +++ b/421m3b93b9/logs/2072596.out @@ -0,0 +1,4089 @@ +Model parameters: d_model 1280 ffw_size 5120 kv_size 128 n_heads 10 n_layers 18 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 18 --hidden-size 1280 --num-attention-heads 10 --kv-channels 128 --ffn-hidden-size 5120 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 1_922_149 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-421m --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 1_922_149 --lr-warmup-samples 19_221 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_421m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_421m --load checkpoints_421m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2072596.json --zero-stage 0 +START 2072596: Fri Nov 25 17:45:22 EET 2022 +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 45.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 45.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 45.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 38.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 36.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 47.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 45.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 44.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 36.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 36.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 44.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 49.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +6: Launching on nid005098 (6/8), master nid005092 port 9999, GPUs 8, CUDA: True +5: Launching on nid005097 (5/8), master nid005092 port 9999, GPUs 8, CUDA: True +3: Launching on nid005095 (3/8), master nid005092 port 9999, GPUs 8, CUDA: True +4: Launching on nid005096 (4/8), master nid005092 port 9999, GPUs 8, CUDA: True +1: Launching on nid005093 (1/8), master nid005092 port 9999, GPUs 8, CUDA: True +0: Launching on nid005092 (0/8), master nid005092 port 9999, GPUs 8, CUDA: True +2: Launching on nid005094 (2/8), master nid005092 port 9999, GPUs 8, CUDA: True +7: Launching on nid005099 (7/8), master nid005092 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... ['/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document'] +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/2072596.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1000 +0: eval_iters ...................................... 1 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 5120 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 1280 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-421m +0: kv_channels ..................................... 128 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_421m +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 1922149 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 19221 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... None +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 10 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 18 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... False +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_421m +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... 949,50,1 +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_421m +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_names ....................... None +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: test_weighted_split_splits ...................... None +0: test_weighted_split_weights ..................... None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 1922149 +0: train_tokens .................................... None +0: train_weighted_split_paths ...................... None +0: train_weighted_split_paths_path ................. None +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... None +0: valid_weighted_split_paths ...................... None +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... None +0: valid_weighted_split_weights .................... None +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2022-11-25 17:46:21,237] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +7: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.090 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: [1/1] c++ scaled_masked_softmax_hip.cuda.o scaled_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib -lamdhip64 -o scaled_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: ninja: no work to do. +0: >>> done with compiling and loading fused kernels. Compilation time: 19.209 seconds +0: time to initialize megatron (seconds): -26.857 +0: [after megatron is initialized] datetime: 2022-11-25 17:46:45 +0: building GPT model ... +0: [2022-11-25 17:46:45,196] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2022-11-25 17:46:45,196] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2022-11-25 17:46:45,196] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 28.84 GB, percent = 5.7% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2022-11-25 17:46:47,208] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=25 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: ParallelTransformerLayerPipe +0: 19: ParallelTransformerLayerPipe +0: 20: ParallelTransformerLayerPipe +0: 21: undo +0: 22: MixedFusedLayerNorm +0: 23: EmbeddingPipe +0: 24: float16_to_fp32 +0: loss: CrossEntropy +0: [2022-11-25 17:46:47,376] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2022-11-25 17:46:47,377] [INFO] [utils.py:828:see_memory_usage] MA 0.79 GB Max_MA 0.79 GB CA 0.86 GB Max_CA 1 GB +0: [2022-11-25 17:46:47,377] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 28.87 GB, percent = 5.7% +0: setting training iterations to 7508 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2022-11-25 17:46:47,379] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2022-11-25 17:47:00,969] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2022-11-25 17:47:00,970] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2022-11-25 17:47:00,970] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2022-11-25 17:47:00,988] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2022-11-25 17:47:00,988] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2022-11-25 17:47:01,037] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2022-11-25 17:47:01,039] [INFO] [utils.py:828:see_memory_usage] MA 0.78 GB Max_MA 0.79 GB CA 0.88 GB Max_CA 1 GB +0: [2022-11-25 17:47:01,039] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.55 GB, percent = 5.9% +3: ninja: no work to do. +3: Time to load utils op: 0.14212846755981445 seconds +0: ninja: no work to do. +0: Time to load utils op: 0.1364896297454834 seconds +3: Time to load utils op: 0.0010764598846435547 seconds +0: Time to load utils op: 0.305586576461792 seconds +7: Time to load utils op: 0.31099605560302734 seconds +2: Time to load utils op: 0.30997800827026367 seconds +0: Time to load utils op: 0.0005908012390136719 seconds +0: Time to load utils op: 0.00039196014404296875 seconds +0: Time to load utils op: 0.2021806240081787 seconds +0: Time to load utils op: 0.201707124710083 seconds +0: Time to load utils op: 0.20219635963439941 seconds +2: Time to load utils op: 0.20375895500183105 seconds +2: Time to load utils op: 0.20399928092956543 seconds +2: Time to load utils op: 0.20429110527038574 secondsTime to load utils op: 0.2040109634399414 seconds +2: +2: Time to load utils op: 0.2045128345489502 seconds +2: Time to load utils op: 0.20450997352600098 seconds +2: Time to load utils op: 0.20430564880371094 seconds +3: Time to load utils op: 0.20435118675231934 seconds +3: Time to load utils op: 0.2044365406036377 seconds +3: Time to load utils op: 0.20415878295898438 seconds +3: Time to load utils op: 0.20419740676879883 secondsTime to load utils op: 0.20368528366088867 secondsTime to load utils op: 0.2045443058013916 seconds +3: Time to load utils op: 0.20388150215148926 seconds +3: +3: +7: Time to load utils op: 0.20267271995544434 seconds +7: Time to load utils op: 0.20203614234924316 seconds +7: Time to load utils op: 0.20164847373962402 seconds +7: Time to load utils op: 0.20231366157531738 seconds +7: Time to load utils op: 0.20172429084777832 seconds +7: Time to load utils op: 0.20189499855041504 seconds +7: Time to load utils op: 0.20177245140075684 seconds +0: Time to load utils op: 0.2028803825378418 seconds +0: Time to load utils op: 0.2032938003540039 seconds +1: Time to load utils op: 0.21158051490783691 secondsTime to load utils op: 0.21158885955810547 secondsTime to load utils op: 0.2115952968597412 secondsTime to load utils op: 0.2115929126739502 seconds +1: +1: Time to load utils op: 0.2115926742553711 seconds +1: +1: +1: Time to load utils op: 0.21159625053405762 seconds +1: Time to load utils op: 0.21160149574279785 secondsTime to load utils op: 0.2116074562072754 seconds +1: +0: Time to load utils op: 0.30336904525756836 seconds +0: Time to load utils op: 0.00039005279541015625 seconds +0: Time to load utils op: 0.00041174888610839844 seconds +4: Time to load utils op: 0.21150445938110352 seconds +4: Time to load utils op: 0.2115182876586914 secondsTime to load utils op: 0.21151995658874512 seconds +4: +4: Time to load utils op: 0.21155047416687012 seconds +4: Time to load utils op: 0.21154284477233887 seconds +4: Time to load utils op: 0.21155357360839844 seconds +4: Time to load utils op: 0.21157073974609375 secondsTime to load utils op: 0.21157050132751465 seconds +4: +5: Time to load utils op: 0.21142911911010742 seconds +5: Time to load utils op: 0.2114424705505371 seconds +5: Time to load utils op: 0.21144866943359375 seconds +5: Time to load utils op: 0.2114555835723877 seconds +5: Time to load utils op: 0.21146202087402344 seconds +5: Time to load utils op: 0.21146941184997559 seconds +5: Time to load utils op: 0.21148371696472168 seconds +5: Time to load utils op: 0.2114872932434082 seconds +6: Time to load utils op: 0.21080303192138672 seconds +6: Time to load utils op: 0.21082377433776855 seconds +6: Time to load utils op: 0.2108137607574463 seconds +6: Time to load utils op: 0.21082639694213867 secondsTime to load utils op: 0.21081829071044922 seconds +6: +6: Time to load utils op: 0.21082615852355957 seconds +6: Time to load utils op: 0.21083474159240723 secondsTime to load utils op: 0.2108321189880371 seconds +6: +3: Time to load utils op: 0.0003466606140136719 seconds +0: Time to load utils op: 0.0003936290740966797 seconds +3: Time to load utils op: 0.00041604042053222656 seconds +3: Time to load utils op: 0.00034332275390625 seconds +3: Time to load utils op: 0.0003864765167236328 seconds +3: Time to load utils op: 0.0003859996795654297 seconds +3: Time to load utils op: 0.00036907196044921875 seconds +3: Time to load utils op: 0.0003609657287597656 seconds +7: Time to load utils op: 0.00038814544677734375 seconds +7: Time to load utils op: 0.0005114078521728516 seconds +7: Time to load utils op: 0.0003540515899658203 seconds +7: Time to load utils op: 0.0003459453582763672 seconds +7: Time to load utils op: 0.0003476142883300781 seconds +7: Time to load utils op: 0.00033736228942871094 seconds +7: Time to load utils op: 0.00036644935607910156 seconds +7: Time to load utils op: 0.00035834312438964844 seconds +0: Time to load utils op: 0.00036025047302246094 seconds +0: Time to load utils op: 0.0004055500030517578 seconds +2: Time to load utils op: 0.0009119510650634766 seconds +2: Time to load utils op: 0.0009627342224121094 seconds +2: Time to load utils op: 0.0012645721435546875 seconds +2: Time to load utils op: 0.0014247894287109375 secondsTime to load utils op: 0.0014121532440185547 seconds +2: +2: Time to load utils op: 0.0014166831970214844 seconds +2: Time to load utils op: 0.0013954639434814453 seconds +2: Time to load utils op: 0.001497030258178711 seconds +0: [2022-11-25 17:47:01,387] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2022-11-25 17:47:01,388] [INFO] [utils.py:828:see_memory_usage] MA 0.78 GB Max_MA 0.78 GB CA 0.88 GB Max_CA 1 GB +0: [2022-11-25 17:47:01,388] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.68 GB, percent = 5.9% +4: Time to load utils op: 0.0007967948913574219 seconds +4: Time to load utils op: 0.0008883476257324219 seconds +4: Time to load utils op: 0.001123666763305664 seconds +4: Time to load utils op: 0.0011439323425292969 seconds +4: Time to load utils op: 0.0011553764343261719 seconds +4: Time to load utils op: 0.0011293888092041016 seconds +4: Time to load utils op: 0.0011966228485107422 seconds +5: Time to load utils op: 0.000896453857421875 seconds +4: Time to load utils op: 0.0011959075927734375 seconds +1: Time to load utils op: 0.0009152889251708984 seconds +1: Time to load utils op: 0.000835418701171875 seconds +5: Time to load utils op: 0.0012240409851074219 seconds +1: Time to load utils op: 0.0012021064758300781 seconds +5: Time to load utils op: 0.0012183189392089844 secondsTime to load utils op: 0.0012583732604980469 seconds +5: +5: Time to load utils op: 0.0012745857238769531 seconds +5: Time to load utils op: 0.001245737075805664 secondsTime to load utils op: 0.0012102127075195312 seconds +5: +5: Time to load utils op: 0.0011985301971435547 seconds +1: Time to load utils op: 0.0013883113861083984 seconds +1: Time to load utils op: 0.001348733901977539 seconds +1: Time to load utils op: 0.0012586116790771484 seconds +1: Time to load utils op: 0.001337289810180664 seconds +1: Time to load utils op: 0.001436471939086914 seconds +6: Time to load utils op: 0.0010688304901123047 secondsTime to load utils op: 0.0010669231414794922 seconds +6: +6: Time to load utils op: 0.0012099742889404297 seconds +6: Time to load utils op: 0.0013346672058105469 seconds +6: Time to load utils op: 0.0012807846069335938 secondsTime to load utils op: 0.0013766288757324219 seconds +6: +6: Time to load utils op: 0.0012848377227783203 seconds +6: Time to load utils op: 0.001332998275756836 seconds +0: [2022-11-25 17:47:01,444] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2022-11-25 17:47:01,445] [INFO] [utils.py:828:see_memory_usage] MA 1.68 GB Max_MA 1.68 GB CA 2.21 GB Max_CA 2 GB +0: [2022-11-25 17:47:01,445] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,483] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2022-11-25 17:47:01,483] [INFO] [utils.py:828:see_memory_usage] MA 1.68 GB Max_MA 1.68 GB CA 2.21 GB Max_CA 2 GB +0: [2022-11-25 17:47:01,484] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,519] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2022-11-25 17:47:01,519] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-25 17:47:01,519] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,550] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2022-11-25 17:47:01,551] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-25 17:47:01,551] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,586] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2022-11-25 17:47:01,586] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-25 17:47:01,586] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,618] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2022-11-25 17:47:01,618] [INFO] [utils.py:828:see_memory_usage] MA 2.38 GB Max_MA 2.38 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-25 17:47:01,619] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,655] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2022-11-25 17:47:01,656] [INFO] [utils.py:828:see_memory_usage] MA 2.43 GB Max_MA 2.43 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-25 17:47:01,656] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,687] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2022-11-25 17:47:01,687] [INFO] [utils.py:828:see_memory_usage] MA 2.43 GB Max_MA 2.43 GB CA 3.23 GB Max_CA 3 GB +0: [2022-11-25 17:47:01,687] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 29.7 GB, percent = 5.9% +0: [2022-11-25 17:47:01,688] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2022-11-25 17:47:01,688] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2022-11-25 17:47:01,688] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2022-11-25 17:47:01,688] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2022-11-25 17:47:01,688] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2022-11-25 17:47:01,688] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2022-11-25 17:47:01,688] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2022-11-25 17:47:01,688] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2022-11-25 17:47:01,688] [INFO] [config.py:1011:print] amp_params ................... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] comms_config ................. +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] dump_state ................... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2022-11-25 17:47:01,689] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] monitor_config ............... +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] pld_params ................... False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2022-11-25 17:47:01,690] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2022-11-25 17:47:01,690] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0003795623779296875 seconds +0: [2022-11-25 17:47:01,691] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2022-11-25 17:47:01,712] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=25 [0, 25) STAGE_PARAMS=421207040 (421.207M) TOTAL_PARAMS=421207040 (421.207M) UNIQUE_PARAMS=421207040 (421.207M) +0: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: WARNING: could not find the metadata file checkpoints_421m +0: will not load any checkpoints and will start from random +0: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,719] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +6: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +4: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +0: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +3: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +5: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +1: [2022-11-25 17:47:01,720] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +2: [2022-11-25 17:47:01,726] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_421m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +7: time (ms) | load-checkpoint: 9.34 +0: estimated model parameters: 0.42120704 +0: estimated model parameters without embeddings: 0.35419648 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-25 17:47:02 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 1922149 +0: validation: 2048 +0: test: 256 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.024032 seconds +0: number of documents: 210604984 +0: > dataset split: +0: train: +0: document indices in [0, 199864130) total of 199864130 documents +0: validation: +0: document indices in [199864130, 210394379) total of 10530249 documents +0: test: +0: document indices in [210394379, 210604984) total of 210605 documents +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 13.979875 +0: using: +0: number of documents: 199864130 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 173377816 +0: > elasped time to build and save sample-idx mapping (seconds): 4.141968 +0: > building shuffle index with split [0, 173377816) and [173377816, 173377816) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 9.271774 +0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_1922149ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_1922149ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_1922149ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.115 seconds +0: total number of samples: 173377817 +0: total number of epochs: 1 +0: > WARNING: could not find index map files, building the indices on rank 0 ... +0: > only one epoch required, setting separate_last_epoch to False +0: > elasped time to build and save doc-idx mapping (seconds): 0.485574 +0: using: +0: number of documents: 10530249 +0: number of epochs: 1 +0: sequence length: 2048 +0: total number of samples: 9118344 +0: > elasped time to build and save sample-idx mapping (seconds): 0.207654 +0: > building shuffle index with split [0, 9118344) and [9118344, 9118344) ... +0: > elasped time to build and save shuffle-idx mapping (seconds): 0.277725 +0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_2048ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_2048ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_2048ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.045 seconds +0: total number of samples: 9118345 +0: total number of epochs: 1 +0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.012 seconds +0: total number of samples: 182928 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2022-11-25 17:47:45 +0: done with setup ... +0: training ... +0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +7: time (ms) | model-and-optimizer-setup: 16950.51 | train/valid/test-data-iterators-setup: 42479.90 +0: [000-000] 0.4212B / 0.3542B +0: [before the start of training step] datetime: 2022-11-25 17:47:45 +0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 4873.00537109375 | max allocated: 27817.7919921875 | reserved: 29816.0 | max reserved: 29816.0 +7: iteration 10/ 7508 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.55 | learning rate: 2.664E-05 | global batch size: 256 | lm loss: 9.801268E+00 | grad norm: 3.805 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 164.978 | TFLOPs: 15.73 | +7: iteration 20/ 7508 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.59 | learning rate: 5.328E-05 | global batch size: 256 | lm loss: 8.555362E+00 | grad norm: 2.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.311 | TFLOPs: 41.31 | +7: iteration 30/ 7508 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.58 | learning rate: 7.991E-05 | global batch size: 256 | lm loss: 7.937711E+00 | grad norm: 1.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.567 | TFLOPs: 41.91 | +7: iteration 40/ 7508 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.60 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 7.284711E+00 | grad norm: 1.582 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.105 | TFLOPs: 40.62 | +7: iteration 50/ 7508 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.58 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 6.929020E+00 | grad norm: 0.666 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.614 | TFLOPs: 42.39 | +7: iteration 60/ 7508 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.60 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 6.739489E+00 | grad norm: 1.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 425.022 | TFLOPs: 40.52 | +7: iteration 70/ 7508 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.60 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 6.509132E+00 | grad norm: 0.865 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.123 | TFLOPs: 40.91 | +7: iteration 80/ 7508 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.61 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.295900E+00 | grad norm: 1.003 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 421.178 | TFLOPs: 40.15 | +7: iteration 90/ 7508 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.59 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.163561E+00 | grad norm: 0.960 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.202 | TFLOPs: 41.59 | +7: iteration 100/ 7508 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.59 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.981005E+00 | grad norm: 0.966 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.023 | TFLOPs: 41.47 | +7: iteration 110/ 7508 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.59 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.860977E+00 | grad norm: 0.732 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.933 | TFLOPs: 41.56 | +7: iteration 120/ 7508 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.58 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.749522E+00 | grad norm: 0.688 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.784 | TFLOPs: 41.93 | +7: iteration 130/ 7508 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.57 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.652393E+00 | grad norm: 0.621 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.382 | TFLOPs: 42.94 | +7: iteration 140/ 7508 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.58 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.584330E+00 | grad norm: 1.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.675 | TFLOPs: 42.11 | +7: iteration 150/ 7508 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.59 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.561489E+00 | grad norm: 0.599 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.082 | TFLOPs: 41.19 | +7: iteration 160/ 7508 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.61 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.456155E+00 | grad norm: 0.636 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.426 | TFLOPs: 40.27 | +7: iteration 170/ 7508 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.59 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.443050E+00 | grad norm: 0.571 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.081 | TFLOPs: 41.29 | +7: iteration 180/ 7508 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.60 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.349088E+00 | grad norm: 0.573 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.185 | TFLOPs: 41.01 | +7: iteration 190/ 7508 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.58 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.327003E+00 | grad norm: 1.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.555 | TFLOPs: 41.91 | +7: iteration 200/ 7508 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.60 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.279213E+00 | grad norm: 0.544 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.728 | TFLOPs: 40.68 | +7: iteration 210/ 7508 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.59 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 5.261644E+00 | grad norm: 0.934 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.264 | TFLOPs: 41.40 | +7: iteration 220/ 7508 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.58 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.205000E+00 | grad norm: 0.604 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.413 | TFLOPs: 41.80 | +7: iteration 230/ 7508 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.58 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.182301E+00 | grad norm: 0.583 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.481 | TFLOPs: 42.28 | +7: iteration 240/ 7508 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.59 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.160447E+00 | grad norm: 0.928 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.170 | TFLOPs: 41.68 | +7: iteration 250/ 7508 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.58 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 5.108447E+00 | grad norm: 1.004 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.638 | TFLOPs: 41.91 | +7: iteration 260/ 7508 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.60 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.102853E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.742 | TFLOPs: 40.49 | +7: iteration 270/ 7508 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.59 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.019958E+00 | grad norm: 0.535 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.303 | TFLOPs: 41.50 | +7: iteration 280/ 7508 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.59 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 5.016301E+00 | grad norm: 0.799 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.967 | TFLOPs: 41.56 | +7: iteration 290/ 7508 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.57 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.957278E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.318 | TFLOPs: 42.46 | +7: iteration 300/ 7508 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.59 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.883797E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.538 | TFLOPs: 41.43 | +7: iteration 310/ 7508 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.59 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 4.916654E+00 | grad norm: 0.580 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.573 | TFLOPs: 41.24 | +7: iteration 320/ 7508 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.62 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.888972E+00 | grad norm: 0.642 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 413.025 | TFLOPs: 39.38 | +7: iteration 330/ 7508 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.58 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 4.872586E+00 | grad norm: 0.715 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.989 | TFLOPs: 41.76 | +7: iteration 340/ 7508 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.59 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.831702E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.383 | TFLOPs: 41.22 | +7: iteration 350/ 7508 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.59 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 4.761525E+00 | grad norm: 0.585 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.537 | TFLOPs: 41.62 | +7: iteration 360/ 7508 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.57 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.728673E+00 | grad norm: 0.847 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.811 | TFLOPs: 42.60 | +7: iteration 370/ 7508 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.58 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.688060E+00 | grad norm: 0.575 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.946 | TFLOPs: 42.04 | +7: iteration 380/ 7508 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.59 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 4.684821E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.894 | TFLOPs: 41.18 | +7: iteration 390/ 7508 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.60 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.621130E+00 | grad norm: 0.768 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.488 | TFLOPs: 40.85 | +7: iteration 400/ 7508 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.59 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 4.643337E+00 | grad norm: 0.660 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.523 | TFLOPs: 41.14 | +7: iteration 410/ 7508 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.61 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 4.593535E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 418.025 | TFLOPs: 39.85 | +7: iteration 420/ 7508 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.59 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.609572E+00 | grad norm: 0.875 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.845 | TFLOPs: 41.46 | +7: iteration 430/ 7508 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.59 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 4.532931E+00 | grad norm: 0.982 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.858 | TFLOPs: 41.17 | +7: iteration 440/ 7508 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.58 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.479342E+00 | grad norm: 0.842 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.786 | TFLOPs: 41.74 | +7: iteration 450/ 7508 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.59 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 4.455965E+00 | grad norm: 0.813 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.094 | TFLOPs: 41.39 | +7: iteration 460/ 7508 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.58 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 4.454931E+00 | grad norm: 0.577 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.688 | TFLOPs: 42.30 | +7: iteration 470/ 7508 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.60 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.420317E+00 | grad norm: 0.604 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 425.283 | TFLOPs: 40.55 | +7: iteration 480/ 7508 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.58 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 4.376651E+00 | grad norm: 0.684 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.196 | TFLOPs: 41.97 | +7: iteration 490/ 7508 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.59 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.313994E+00 | grad norm: 0.975 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.501 | TFLOPs: 41.14 | +7: iteration 500/ 7508 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.60 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 4.310555E+00 | grad norm: 0.975 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.541 | TFLOPs: 40.76 | +7: iteration 510/ 7508 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.59 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 4.267378E+00 | grad norm: 0.546 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.841 | TFLOPs: 41.08 | +7: iteration 520/ 7508 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.58 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 4.210854E+00 | grad norm: 0.920 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.036 | TFLOPs: 42.33 | +7: iteration 530/ 7508 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.60 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.142874E+00 | grad norm: 0.966 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.646 | TFLOPs: 40.87 | +7: iteration 540/ 7508 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.61 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 4.154507E+00 | grad norm: 0.883 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.590 | TFLOPs: 40.29 | +7: iteration 550/ 7508 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.59 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 4.125101E+00 | grad norm: 0.921 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.722 | TFLOPs: 41.45 | +7: iteration 560/ 7508 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.59 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 4.087883E+00 | grad norm: 0.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.272 | TFLOPs: 41.40 | +7: iteration 570/ 7508 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.57 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.982997E+00 | grad norm: 1.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.655 | TFLOPs: 42.97 | +7: iteration 580/ 7508 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.61 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.914655E+00 | grad norm: 0.705 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 420.203 | TFLOPs: 40.06 | +7: iteration 590/ 7508 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.61 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.847444E+00 | grad norm: 0.578 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.634 | TFLOPs: 40.29 | +7: iteration 600/ 7508 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.60 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.822655E+00 | grad norm: 0.760 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 425.623 | TFLOPs: 40.58 | +7: iteration 610/ 7508 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.59 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.816843E+00 | grad norm: 0.536 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.415 | TFLOPs: 41.61 | +7: iteration 620/ 7508 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.59 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.751604E+00 | grad norm: 0.585 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.353 | TFLOPs: 41.41 | +7: iteration 630/ 7508 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.57 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.797701E+00 | grad norm: 0.725 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.858 | TFLOPs: 42.60 | +7: iteration 640/ 7508 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.58 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.706129E+00 | grad norm: 0.734 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.902 | TFLOPs: 41.84 | +7: iteration 650/ 7508 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.59 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.717591E+00 | grad norm: 0.727 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.494 | TFLOPs: 41.61 | +7: iteration 660/ 7508 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.59 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.670375E+00 | grad norm: 0.468 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.616 | TFLOPs: 41.34 | +7: iteration 670/ 7508 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.61 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.605450E+00 | grad norm: 0.609 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 419.536 | TFLOPs: 40.00 | +7: iteration 680/ 7508 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.59 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.612383E+00 | grad norm: 0.599 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.339 | TFLOPs: 41.70 | +7: iteration 690/ 7508 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.59 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.612547E+00 | grad norm: 0.537 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.849 | TFLOPs: 41.27 | +7: iteration 700/ 7508 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.58 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.586592E+00 | grad norm: 0.567 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.125 | TFLOPs: 42.06 | +7: iteration 710/ 7508 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.60 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.575414E+00 | grad norm: 0.678 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.154 | TFLOPs: 40.82 | +7: iteration 720/ 7508 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.59 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.611619E+00 | grad norm: 0.570 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.627 | TFLOPs: 41.06 | +7: iteration 730/ 7508 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.59 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.576100E+00 | grad norm: 0.565 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.944 | TFLOPs: 41.28 | +7: iteration 740/ 7508 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.60 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.536127E+00 | grad norm: 0.662 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 423.603 | TFLOPs: 40.39 | +7: iteration 750/ 7508 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.57 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.498634E+00 | grad norm: 0.538 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.949 | TFLOPs: 42.71 | +7: iteration 760/ 7508 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.59 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.535741E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.646 | TFLOPs: 41.63 | +7: iteration 770/ 7508 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.58 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.536231E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.649 | TFLOPs: 41.92 | +7: iteration 780/ 7508 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.58 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.467702E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.329 | TFLOPs: 42.08 | +7: iteration 790/ 7508 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.59 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.448446E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.218 | TFLOPs: 41.59 | +7: iteration 800/ 7508 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.60 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.433945E+00 | grad norm: 0.513 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 425.282 | TFLOPs: 40.55 | +7: iteration 810/ 7508 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.59 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.421304E+00 | grad norm: 0.487 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.695 | TFLOPs: 41.06 | +7: iteration 820/ 7508 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.57 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.431895E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.396 | TFLOPs: 43.13 | +7: iteration 830/ 7508 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.58 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.449043E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.026 | TFLOPs: 41.95 | +7: iteration 840/ 7508 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.58 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.378618E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.504 | TFLOPs: 41.81 | +7: iteration 850/ 7508 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.60 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.386469E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.057 | TFLOPs: 40.81 | +7: iteration 860/ 7508 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.57 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.373400E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.181 | TFLOPs: 42.82 | +7: iteration 870/ 7508 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.57 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.401056E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.622 | TFLOPs: 42.58 | +7: iteration 880/ 7508 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.58 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.402568E+00 | grad norm: 0.532 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.299 | TFLOPs: 41.98 | +7: iteration 890/ 7508 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.59 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.360046E+00 | grad norm: 0.510 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.852 | TFLOPs: 41.55 | +7: iteration 900/ 7508 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.58 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.341151E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.094 | TFLOPs: 42.15 | +7: iteration 910/ 7508 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.57 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.366449E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.428 | TFLOPs: 42.56 | +7: iteration 920/ 7508 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.59 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.360683E+00 | grad norm: 0.535 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.300 | TFLOPs: 41.22 | +7: iteration 930/ 7508 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.60 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.310853E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.680 | TFLOPs: 40.68 | +7: iteration 940/ 7508 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.59 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.301548E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.768 | TFLOPs: 41.26 | +7: iteration 950/ 7508 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.60 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.314966E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.884 | TFLOPs: 40.89 | +7: iteration 960/ 7508 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.59 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.308403E+00 | grad norm: 0.541 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.353 | TFLOPs: 41.51 | +7: iteration 970/ 7508 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.59 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.313172E+00 | grad norm: 0.695 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.242 | TFLOPs: 41.30 | +7: iteration 980/ 7508 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.60 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.271169E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.246 | TFLOPs: 41.02 | +7: iteration 990/ 7508 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.57 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.282766E+00 | grad norm: 0.432 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.866 | TFLOPs: 42.60 | +7: iteration 1000/ 7508 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.60 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.260793E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.068 | TFLOPs: 40.72 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 1000 | lm loss value: 3.217661E+00 | lm loss PPL: 2.496965E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 1000 to checkpoints_421m +0: [2022-11-25 17:57:44,500] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +0: [2022-11-25 17:57:44,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_01-model_00-model_states.pt... +0: [2022-11-25 17:57:44,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_01-model_00-model_states.pt. +0: [2022-11-25 17:57:44,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_03-model_00-model_states.pt... +0: [2022-11-25 17:57:44,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_03-model_00-model_states.pt. +0: [2022-11-25 17:57:44,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_04-model_00-model_states.pt... +0: [2022-11-25 17:57:44,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_04-model_00-model_states.pt. +0: [2022-11-25 17:57:44,749] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_05-model_00-model_states.pt... +0: [2022-11-25 17:57:44,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_05-model_00-model_states.pt. +0: [2022-11-25 17:57:44,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_06-model_00-model_states.pt... +0: [2022-11-25 17:57:44,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_06-model_00-model_states.pt. +0: [2022-11-25 17:57:44,829] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_07-model_00-model_states.pt... +0: [2022-11-25 17:57:44,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_07-model_00-model_states.pt. +0: [2022-11-25 17:57:44,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_08-model_00-model_states.pt... +0: [2022-11-25 17:57:44,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_08-model_00-model_states.pt. +0: [2022-11-25 17:57:44,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_09-model_00-model_states.pt... +0: [2022-11-25 17:57:44,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_09-model_00-model_states.pt. +0: [2022-11-25 17:57:44,949] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_10-model_00-model_states.pt... +0: [2022-11-25 17:57:44,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_10-model_00-model_states.pt. +0: [2022-11-25 17:57:44,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_11-model_00-model_states.pt... +0: [2022-11-25 17:57:45,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_11-model_00-model_states.pt. +0: [2022-11-25 17:57:45,031] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_12-model_00-model_states.pt... +0: [2022-11-25 17:57:45,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_12-model_00-model_states.pt. +0: [2022-11-25 17:57:45,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_13-model_00-model_states.pt... +0: [2022-11-25 17:57:45,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_13-model_00-model_states.pt. +0: [2022-11-25 17:57:45,111] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_14-model_00-model_states.pt... +0: [2022-11-25 17:57:45,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_14-model_00-model_states.pt. +0: [2022-11-25 17:57:45,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_15-model_00-model_states.pt... +0: [2022-11-25 17:57:45,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_15-model_00-model_states.pt. +0: [2022-11-25 17:57:45,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_16-model_00-model_states.pt... +0: [2022-11-25 17:57:45,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_16-model_00-model_states.pt. +0: [2022-11-25 17:57:45,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_17-model_00-model_states.pt... +0: [2022-11-25 17:57:45,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_17-model_00-model_states.pt. +0: [2022-11-25 17:57:45,268] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_18-model_00-model_states.pt... +0: [2022-11-25 17:57:45,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_18-model_00-model_states.pt. +0: [2022-11-25 17:57:45,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_19-model_00-model_states.pt... +0: [2022-11-25 17:57:45,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_19-model_00-model_states.pt. +0: [2022-11-25 17:57:45,347] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_20-model_00-model_states.pt... +0: [2022-11-25 17:57:45,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_20-model_00-model_states.pt. +0: [2022-11-25 17:57:45,386] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/layer_22-model_00-model_states.pt... +0: [2022-11-25 17:57:45,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/layer_22-model_00-model_states.pt. +0: [2022-11-25 17:57:45,391] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step1000/mp_rank_00_model_states.pt +0: [2022-11-25 17:57:45,391] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/mp_rank_00_model_states.pt... +0: [2022-11-25 17:57:45,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/mp_rank_00_model_states.pt. +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +0: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +4: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +6: [2022-11-25 17:57:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +7: [2022-11-25 17:57:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 17:57:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +1: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +5: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 17:57:45,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 17:57:45,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +4: [2022-11-25 17:57:45,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 17:57:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 17:57:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +7: [2022-11-25 17:57:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +6: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 17:57:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 17:57:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 17:57:45,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 17:57:45,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-25 17:57:45,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +3: [2022-11-25 17:57:45,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-25 17:57:45,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 17:57:45,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +2: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-25 17:57:45,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-25 17:57:45,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: [2022-11-25 17:57:45,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 17:57:45,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +0: successfully saved checkpoint at iteration 1000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1156.33 +7: iteration 1010/ 7508 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.72 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.289999E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.914 | TFLOPs: 33.84 | +7: iteration 1020/ 7508 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.57 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.258988E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.769 | TFLOPs: 42.69 | +7: iteration 1030/ 7508 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.59 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.248538E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.633 | TFLOPs: 41.25 | +7: iteration 1040/ 7508 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.59 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.290600E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.274 | TFLOPs: 41.31 | +7: iteration 1050/ 7508 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.61 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.277945E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 421.956 | TFLOPs: 40.23 | +7: iteration 1060/ 7508 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.58 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.231615E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.061 | TFLOPs: 41.96 | +7: iteration 1070/ 7508 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.58 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.223788E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.535 | TFLOPs: 41.81 | +7: iteration 1080/ 7508 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.58 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.177797E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.306 | TFLOPs: 41.98 | +7: iteration 1090/ 7508 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.58 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.205589E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.391 | TFLOPs: 42.37 | +7: iteration 1100/ 7508 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.58 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.239230E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.833 | TFLOPs: 42.41 | +7: iteration 1110/ 7508 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.58 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.191825E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.060 | TFLOPs: 42.05 | +7: iteration 1120/ 7508 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.58 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.217592E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.017 | TFLOPs: 41.95 | +7: iteration 1130/ 7508 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.59 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.217548E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.466 | TFLOPs: 41.42 | +7: iteration 1140/ 7508 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.59 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.175422E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.796 | TFLOPs: 41.64 | +7: iteration 1150/ 7508 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.61 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.208307E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.783 | TFLOPs: 40.31 | +7: iteration 1160/ 7508 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.57 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.190272E+00 | grad norm: 0.527 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.333 | TFLOPs: 42.46 | +7: iteration 1170/ 7508 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.60 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.188508E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.825 | TFLOPs: 40.79 | +7: iteration 1180/ 7508 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.58 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.202043E+00 | grad norm: 0.434 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.064 | TFLOPs: 42.43 | +7: iteration 1190/ 7508 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.60 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.213641E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.713 | TFLOPs: 40.78 | +7: iteration 1200/ 7508 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.59 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.179895E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.205 | TFLOPs: 41.21 | +7: iteration 1210/ 7508 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.59 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.171011E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.109 | TFLOPs: 41.20 | +7: iteration 1220/ 7508 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.59 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.111112E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.921 | TFLOPs: 41.08 | +7: iteration 1230/ 7508 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.57 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.164721E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.555 | TFLOPs: 42.57 | +7: iteration 1240/ 7508 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.59 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.142147E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.098 | TFLOPs: 41.48 | +7: iteration 1250/ 7508 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.59 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.143581E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.111 | TFLOPs: 41.20 | +7: iteration 1260/ 7508 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.59 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.084521E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.750 | TFLOPs: 41.45 | +7: iteration 1270/ 7508 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.60 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.143128E+00 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.438 | TFLOPs: 40.66 | +7: iteration 1280/ 7508 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.60 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.149754E+00 | grad norm: 0.464 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 423.817 | TFLOPs: 40.41 | +7: iteration 1290/ 7508 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.58 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.033779E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.495 | TFLOPs: 41.90 | +7: iteration 1300/ 7508 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.58 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.112243E+00 | grad norm: 0.459 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.051 | TFLOPs: 42.14 | +7: iteration 1310/ 7508 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.58 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.094776E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.929 | TFLOPs: 42.04 | +7: iteration 1320/ 7508 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.58 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.088614E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.102 | TFLOPs: 42.24 | +7: iteration 1330/ 7508 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.58 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.094345E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.244 | TFLOPs: 41.97 | +7: iteration 1340/ 7508 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.60 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.105733E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.664 | TFLOPs: 40.96 | +7: iteration 1350/ 7508 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.58 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.080106E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.679 | TFLOPs: 42.20 | +7: iteration 1360/ 7508 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.58 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.045287E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.752 | TFLOPs: 42.40 | +7: iteration 1370/ 7508 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.58 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.085593E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.729 | TFLOPs: 41.73 | +7: iteration 1380/ 7508 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.59 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.079389E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.188 | TFLOPs: 41.11 | +7: iteration 1390/ 7508 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.58 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.074082E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.339 | TFLOPs: 42.17 | +7: iteration 1400/ 7508 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.57 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.115737E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.269 | TFLOPs: 42.74 | +7: iteration 1410/ 7508 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.59 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.079219E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.126 | TFLOPs: 41.39 | +7: iteration 1420/ 7508 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.56 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.030223E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.664 | TFLOPs: 43.73 | +7: iteration 1430/ 7508 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.59 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.035659E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.250 | TFLOPs: 41.21 | +7: iteration 1440/ 7508 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.57 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.066572E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.639 | TFLOPs: 42.49 | +7: iteration 1450/ 7508 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.60 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.055843E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.709 | TFLOPs: 40.87 | +7: iteration 1460/ 7508 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.56 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.065449E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.000 | TFLOPs: 43.28 | +7: iteration 1470/ 7508 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.57 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.031705E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.123 | TFLOPs: 42.72 | +7: iteration 1480/ 7508 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.58 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.056742E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.243 | TFLOPs: 42.26 | +7: iteration 1490/ 7508 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.57 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.071343E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.446 | TFLOPs: 42.56 | +7: iteration 1500/ 7508 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.58 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.044419E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.993 | TFLOPs: 41.85 | +7: iteration 1510/ 7508 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.57 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.045156E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.307 | TFLOPs: 42.84 | +7: iteration 1520/ 7508 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.57 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.060696E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.442 | TFLOPs: 42.47 | +7: iteration 1530/ 7508 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.60 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.038011E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.684 | TFLOPs: 40.49 | +7: iteration 1540/ 7508 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.58 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.048078E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.753 | TFLOPs: 42.31 | +7: iteration 1550/ 7508 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.57 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.022165E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.401 | TFLOPs: 42.56 | +7: iteration 1560/ 7508 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.57 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.001087E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.020 | TFLOPs: 42.62 | +7: iteration 1570/ 7508 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.58 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 2.991759E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.428 | TFLOPs: 41.99 | +7: iteration 1580/ 7508 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.58 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.018213E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.681 | TFLOPs: 42.30 | +7: iteration 1590/ 7508 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.57 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.022839E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.017 | TFLOPs: 42.52 | +7: iteration 1600/ 7508 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.61 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 2.993423E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 416.912 | TFLOPs: 39.75 | +7: iteration 1610/ 7508 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.58 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 2.977420E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.496 | TFLOPs: 42.38 | +7: iteration 1620/ 7508 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.58 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 2.975409E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.641 | TFLOPs: 42.11 | +7: iteration 1630/ 7508 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.60 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 2.991404E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.322 | TFLOPs: 40.93 | +7: iteration 1640/ 7508 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.58 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 2.964995E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.855 | TFLOPs: 42.32 | +7: iteration 1650/ 7508 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.58 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.024966E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.445 | TFLOPs: 41.90 | +7: iteration 1660/ 7508 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.58 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 2.953894E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.757 | TFLOPs: 42.40 | +7: iteration 1670/ 7508 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.58 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 2.989109E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.212 | TFLOPs: 42.06 | +7: iteration 1680/ 7508 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.59 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 2.963416E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.189 | TFLOPs: 41.20 | +7: iteration 1690/ 7508 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.59 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.010936E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.640 | TFLOPs: 41.06 | +7: iteration 1700/ 7508 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.58 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.004000E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.399 | TFLOPs: 42.18 | +7: iteration 1710/ 7508 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.58 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 2.974519E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.617 | TFLOPs: 42.10 | +7: iteration 1720/ 7508 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.57 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 2.968154E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.759 | TFLOPs: 42.69 | +7: iteration 1730/ 7508 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.58 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 2.958752E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.086 | TFLOPs: 41.77 | +7: iteration 1740/ 7508 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.59 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 2.995363E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.441 | TFLOPs: 41.71 | +7: iteration 1750/ 7508 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.60 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 2.967524E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.413 | TFLOPs: 40.75 | +7: iteration 1760/ 7508 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.59 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 2.979627E+00 | grad norm: 0.471 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.027 | TFLOPs: 41.19 | +7: iteration 1770/ 7508 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.57 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 2.945933E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.257 | TFLOPs: 42.74 | +7: iteration 1780/ 7508 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.58 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 2.936270E+00 | grad norm: 0.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.990 | TFLOPs: 41.76 | +7: iteration 1790/ 7508 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.60 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 2.989422E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.460 | TFLOPs: 40.75 | +7: iteration 1800/ 7508 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.58 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 2.927828E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.957 | TFLOPs: 42.33 | +7: iteration 1810/ 7508 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.59 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 2.958578E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.688 | TFLOPs: 41.63 | +7: iteration 1820/ 7508 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.58 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 2.941776E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.490 | TFLOPs: 42.09 | +7: iteration 1830/ 7508 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.57 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 2.930071E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.545 | TFLOPs: 42.57 | +7: iteration 1840/ 7508 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.58 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 2.930761E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.422 | TFLOPs: 42.08 | +7: iteration 1850/ 7508 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.57 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 2.938527E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.922 | TFLOPs: 42.51 | +7: iteration 1860/ 7508 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.60 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 2.898927E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.489 | TFLOPs: 40.47 | +7: iteration 1870/ 7508 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.57 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 2.910041E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.246 | TFLOPs: 43.02 | +7: iteration 1880/ 7508 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.58 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 2.892108E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.339 | TFLOPs: 42.08 | +7: iteration 1890/ 7508 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.58 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 2.941221E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.177 | TFLOPs: 42.25 | +7: iteration 1900/ 7508 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.59 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 2.879466E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.420 | TFLOPs: 41.61 | +7: iteration 1910/ 7508 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.57 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 2.934339E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.796 | TFLOPs: 42.98 | +7: iteration 1920/ 7508 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.58 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 2.899867E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.833 | TFLOPs: 42.22 | +7: iteration 1930/ 7508 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.57 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 2.913164E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.904 | TFLOPs: 42.80 | +7: iteration 1940/ 7508 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.57 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 2.901938E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.733 | TFLOPs: 43.07 | +7: iteration 1950/ 7508 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.57 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 2.881297E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.145 | TFLOPs: 43.01 | +7: iteration 1960/ 7508 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.59 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 2.937822E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.290 | TFLOPs: 41.40 | +7: iteration 1970/ 7508 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.57 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 2.937020E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.169 | TFLOPs: 42.92 | +7: iteration 1980/ 7508 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.59 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 2.906311E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.775 | TFLOPs: 41.64 | +7: iteration 1990/ 7508 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.60 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 2.935077E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.584 | TFLOPs: 40.96 | +0: [2022-11-25 18:07:28,620] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00017182361507925355, 0.00017182361507925355, 0.00017182361507925355], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 2000/ 7508 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.58 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 2.925786E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.130 | TFLOPs: 41.87 | +0: steps: 2000 loss: 3.0021 iter time (s): 0.589 samples/sec: 434.981 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 2000 | lm loss value: 2.806661E+00 | lm loss PPL: 1.655455E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 2000 to checkpoints_421m +0: [2022-11-25 18:07:28,824] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +0: [2022-11-25 18:07:28,828] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_01-model_00-model_states.pt... +0: [2022-11-25 18:07:28,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_01-model_00-model_states.pt. +0: [2022-11-25 18:07:28,968] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_03-model_00-model_states.pt... +0: [2022-11-25 18:07:29,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_03-model_00-model_states.pt. +0: [2022-11-25 18:07:29,010] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_04-model_00-model_states.pt... +0: [2022-11-25 18:07:29,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_04-model_00-model_states.pt. +0: [2022-11-25 18:07:29,052] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_05-model_00-model_states.pt... +0: [2022-11-25 18:07:29,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_05-model_00-model_states.pt. +0: [2022-11-25 18:07:29,092] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_06-model_00-model_states.pt... +0: [2022-11-25 18:07:29,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_06-model_00-model_states.pt. +0: [2022-11-25 18:07:29,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_07-model_00-model_states.pt... +0: [2022-11-25 18:07:29,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_07-model_00-model_states.pt. +0: [2022-11-25 18:07:29,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_08-model_00-model_states.pt... +0: [2022-11-25 18:07:29,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_08-model_00-model_states.pt. +0: [2022-11-25 18:07:29,215] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_09-model_00-model_states.pt... +0: [2022-11-25 18:07:29,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_09-model_00-model_states.pt. +0: [2022-11-25 18:07:29,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_10-model_00-model_states.pt... +0: [2022-11-25 18:07:29,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_10-model_00-model_states.pt. +0: [2022-11-25 18:07:29,295] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_11-model_00-model_states.pt... +0: [2022-11-25 18:07:29,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_11-model_00-model_states.pt. +0: [2022-11-25 18:07:29,340] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_12-model_00-model_states.pt... +0: [2022-11-25 18:07:29,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_12-model_00-model_states.pt. +0: [2022-11-25 18:07:29,378] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_13-model_00-model_states.pt... +0: [2022-11-25 18:07:29,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_13-model_00-model_states.pt. +0: [2022-11-25 18:07:29,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_14-model_00-model_states.pt... +0: [2022-11-25 18:07:29,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_14-model_00-model_states.pt. +0: [2022-11-25 18:07:29,459] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_15-model_00-model_states.pt... +0: [2022-11-25 18:07:29,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_15-model_00-model_states.pt. +0: [2022-11-25 18:07:29,500] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_16-model_00-model_states.pt... +0: [2022-11-25 18:07:29,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_16-model_00-model_states.pt. +0: [2022-11-25 18:07:29,540] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_17-model_00-model_states.pt... +0: [2022-11-25 18:07:29,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_17-model_00-model_states.pt. +0: [2022-11-25 18:07:29,579] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_18-model_00-model_states.pt... +0: [2022-11-25 18:07:29,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_18-model_00-model_states.pt. +0: [2022-11-25 18:07:29,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_19-model_00-model_states.pt... +0: [2022-11-25 18:07:29,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_19-model_00-model_states.pt. +0: [2022-11-25 18:07:29,661] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_20-model_00-model_states.pt... +0: [2022-11-25 18:07:29,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_20-model_00-model_states.pt. +0: [2022-11-25 18:07:29,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/layer_22-model_00-model_states.pt... +0: [2022-11-25 18:07:29,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/layer_22-model_00-model_states.pt. +0: [2022-11-25 18:07:29,705] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step2000/mp_rank_00_model_states.pt +0: [2022-11-25 18:07:29,705] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/mp_rank_00_model_states.pt... +0: [2022-11-25 18:07:29,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/mp_rank_00_model_states.pt. +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:07:29,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:07:29,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +3: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +7: [2022-11-25 18:07:29,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:07:29,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +2: [2022-11-25 18:07:29,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +7: [2022-11-25 18:07:29,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +2: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 18:07:29,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +1: [2022-11-25 18:07:29,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:07:29,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +6: [2022-11-25 18:07:29,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:07:29,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-25 18:07:29,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +4: [2022-11-25 18:07:29,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:07:29,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 18:07:29,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +5: [2022-11-25 18:07:29,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:07:29,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 18:07:29,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,913] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,913] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: [2022-11-25 18:07:29,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:07:29,938] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 18:07:29,938] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +0: successfully saved checkpoint at iteration 2000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1119.95 +7: iteration 2010/ 7508 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.70 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 2.934872E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 363.876 | TFLOPs: 34.69 | +7: iteration 2020/ 7508 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.58 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 2.948543E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.979 | TFLOPs: 42.42 | +7: iteration 2030/ 7508 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.57 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 2.871001E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.146 | TFLOPs: 42.63 | +7: iteration 2040/ 7508 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.58 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 2.895807E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.140 | TFLOPs: 41.96 | +7: iteration 2050/ 7508 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.59 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 2.923591E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.390 | TFLOPs: 41.41 | +7: iteration 2060/ 7508 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.58 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 2.895893E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.899 | TFLOPs: 42.42 | +7: iteration 2070/ 7508 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.57 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 2.875712E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.148 | TFLOPs: 42.54 | +7: iteration 2080/ 7508 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.59 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 2.894899E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.617 | TFLOPs: 41.34 | +7: iteration 2090/ 7508 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.59 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 2.886672E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.527 | TFLOPs: 41.14 | +7: iteration 2100/ 7508 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.58 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 2.877121E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.205 | TFLOPs: 41.78 | +7: iteration 2110/ 7508 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.58 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 2.864148E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.371 | TFLOPs: 41.98 | +7: iteration 2120/ 7508 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.59 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 2.879621E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.966 | TFLOPs: 41.28 | +7: iteration 2130/ 7508 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.57 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 2.880155E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.292 | TFLOPs: 42.55 | +7: iteration 2140/ 7508 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.57 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 2.876036E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.448 | TFLOPs: 42.56 | +7: iteration 2150/ 7508 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.59 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 2.864549E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.660 | TFLOPs: 41.06 | +7: iteration 2160/ 7508 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.58 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 2.868655E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.626 | TFLOPs: 42.29 | +7: iteration 2170/ 7508 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.58 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 2.883741E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.057 | TFLOPs: 42.15 | +7: iteration 2180/ 7508 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.59 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 2.892548E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.329 | TFLOPs: 41.60 | +7: iteration 2190/ 7508 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.58 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 2.869992E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.829 | TFLOPs: 42.03 | +7: iteration 2200/ 7508 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.57 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 2.983496E+00 | grad norm: 16.399 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.264 | TFLOPs: 42.45 | +7: iteration 2210/ 7508 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.58 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.137754E+00 | grad norm: 1.742 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.851 | TFLOPs: 41.74 | +7: iteration 2220/ 7508 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.57 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.088055E+00 | grad norm: 0.675 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.245 | TFLOPs: 42.64 | +7: iteration 2230/ 7508 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.57 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 2.959972E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.294 | TFLOPs: 42.74 | +7: iteration 2240/ 7508 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.58 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 2.944508E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.647 | TFLOPs: 42.39 | +7: iteration 2250/ 7508 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.59 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 2.887925E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.198 | TFLOPs: 41.40 | +7: iteration 2260/ 7508 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.57 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 2.844704E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.666 | TFLOPs: 42.58 | +7: iteration 2270/ 7508 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.56 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 2.841687E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.602 | TFLOPs: 43.53 | +7: iteration 2280/ 7508 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.58 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 2.864590E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.587 | TFLOPs: 42.10 | +7: iteration 2290/ 7508 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.60 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 2.892356E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.573 | TFLOPs: 40.76 | +7: iteration 2300/ 7508 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.57 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 2.863402E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.920 | TFLOPs: 42.51 | +7: iteration 2310/ 7508 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.59 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 2.885304E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.722 | TFLOPs: 41.54 | +7: iteration 2320/ 7508 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.59 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 2.875444E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.346 | TFLOPs: 41.31 | +7: iteration 2330/ 7508 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.58 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 2.805007E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.796 | TFLOPs: 41.74 | +7: iteration 2340/ 7508 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.58 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 2.818967E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.312 | TFLOPs: 42.36 | +7: iteration 2350/ 7508 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.57 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 2.845208E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.756 | TFLOPs: 42.97 | +7: iteration 2360/ 7508 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.58 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 2.863108E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.539 | TFLOPs: 41.91 | +7: iteration 2370/ 7508 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.57 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 2.872780E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.288 | TFLOPs: 42.74 | +7: iteration 2380/ 7508 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.56 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 2.852276E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.873 | TFLOPs: 43.37 | +7: iteration 2390/ 7508 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.58 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 2.838919E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.135 | TFLOPs: 42.25 | +7: iteration 2400/ 7508 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.58 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 2.883767E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.993 | TFLOPs: 42.23 | +7: iteration 2410/ 7508 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.57 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 2.846115E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.432 | TFLOPs: 42.75 | +7: iteration 2420/ 7508 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.57 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 2.837594E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.269 | TFLOPs: 42.83 | +7: iteration 2430/ 7508 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.58 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 2.842517E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.505 | TFLOPs: 41.81 | +7: iteration 2440/ 7508 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.58 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 2.814774E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.905 | TFLOPs: 42.04 | +7: iteration 2450/ 7508 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.58 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 2.853564E+00 | grad norm: 0.435 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.413 | TFLOPs: 42.27 | +7: iteration 2460/ 7508 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.58 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 2.875596E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.323 | TFLOPs: 42.17 | +7: iteration 2470/ 7508 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.59 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 2.839893E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.395 | TFLOPs: 41.32 | +7: iteration 2480/ 7508 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.59 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 2.815832E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.365 | TFLOPs: 41.32 | +7: iteration 2490/ 7508 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.58 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 2.812180E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.200 | TFLOPs: 41.97 | +7: iteration 2500/ 7508 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.57 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 2.835678E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.932 | TFLOPs: 42.51 | +7: iteration 2510/ 7508 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.59 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 2.850321E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.168 | TFLOPs: 41.39 | +7: iteration 2520/ 7508 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.56 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 2.806200E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.396 | TFLOPs: 43.32 | +7: iteration 2530/ 7508 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.57 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 2.819374E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.210 | TFLOPs: 42.83 | +7: iteration 2540/ 7508 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.58 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 2.801744E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.700 | TFLOPs: 41.92 | +7: iteration 2550/ 7508 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.58 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 2.778941E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.339 | TFLOPs: 41.98 | +7: iteration 2560/ 7508 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.59 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 2.791152E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.415 | TFLOPs: 41.51 | +7: iteration 2570/ 7508 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.59 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 2.805201E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.293 | TFLOPs: 41.69 | +7: iteration 2580/ 7508 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.58 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 2.810114E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.864 | TFLOPs: 42.03 | +7: iteration 2590/ 7508 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.58 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 2.833381E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.719 | TFLOPs: 41.83 | +7: iteration 2600/ 7508 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.60 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 2.781748E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.868 | TFLOPs: 40.70 | +7: iteration 2610/ 7508 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.58 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 2.818849E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.250 | TFLOPs: 42.35 | +7: iteration 2620/ 7508 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.60 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 2.828582E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.518 | TFLOPs: 40.95 | +7: iteration 2630/ 7508 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.59 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 2.801032E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.473 | TFLOPs: 41.61 | +7: iteration 2640/ 7508 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.57 | learning rate: 1.521E-04 | global batch size: 256 | lm loss: 2.848745E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.078 | TFLOPs: 42.91 | +7: iteration 2650/ 7508 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.59 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 2.814683E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.220 | TFLOPs: 41.68 | +7: iteration 2660/ 7508 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.58 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 2.785699E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.962 | TFLOPs: 41.95 | +7: iteration 2670/ 7508 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.59 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 2.793686E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.216 | TFLOPs: 41.59 | +7: iteration 2680/ 7508 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.58 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 2.759969E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.376 | TFLOPs: 42.18 | +7: iteration 2690/ 7508 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.58 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 2.785228E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.230 | TFLOPs: 41.78 | +7: iteration 2700/ 7508 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.57 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 2.797971E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.636 | TFLOPs: 42.68 | +7: iteration 2710/ 7508 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.57 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 2.758682E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.687 | TFLOPs: 42.97 | +7: iteration 2720/ 7508 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.57 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 2.818062E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.052 | TFLOPs: 42.72 | +7: iteration 2730/ 7508 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.60 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 2.776557E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.163 | TFLOPs: 40.73 | +7: iteration 2740/ 7508 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.58 | learning rate: 1.487E-04 | global batch size: 256 | lm loss: 2.752993E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.434 | TFLOPs: 42.37 | +7: iteration 2750/ 7508 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.57 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 2.762142E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.322 | TFLOPs: 42.55 | +7: iteration 2760/ 7508 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.59 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 2.775889E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.868 | TFLOPs: 41.65 | +7: iteration 2770/ 7508 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.57 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 2.800144E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.764 | TFLOPs: 42.50 | +7: iteration 2780/ 7508 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.57 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 2.788220E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.192 | TFLOPs: 43.11 | +7: iteration 2790/ 7508 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.59 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 2.801869E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.233 | TFLOPs: 41.11 | +7: iteration 2800/ 7508 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.58 | learning rate: 1.466E-04 | global batch size: 256 | lm loss: 2.824371E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.861 | TFLOPs: 42.41 | +7: iteration 2810/ 7508 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.57 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 2.743118E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.974 | TFLOPs: 42.52 | +7: iteration 2820/ 7508 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.57 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 2.817148E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.903 | TFLOPs: 42.99 | +7: iteration 2830/ 7508 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.58 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 2.808565E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.085 | TFLOPs: 41.77 | +7: iteration 2840/ 7508 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.58 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 2.765893E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.004 | TFLOPs: 42.14 | +7: iteration 2850/ 7508 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.57 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 2.786926E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.653 | TFLOPs: 42.96 | +7: iteration 2860/ 7508 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.57 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 2.782241E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.382 | TFLOPs: 42.84 | +7: iteration 2870/ 7508 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.57 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 2.791059E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.243 | TFLOPs: 42.45 | +7: iteration 2880/ 7508 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.58 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 2.778728E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.140 | TFLOPs: 41.77 | +7: iteration 2890/ 7508 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.61 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 2.760827E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 419.956 | TFLOPs: 40.04 | +7: iteration 2900/ 7508 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.58 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 2.764922E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.314 | TFLOPs: 41.79 | +7: iteration 2910/ 7508 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.58 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 2.771723E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.121 | TFLOPs: 42.06 | +7: iteration 2920/ 7508 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.58 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 2.733078E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.430 | TFLOPs: 41.89 | +7: iteration 2930/ 7508 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.58 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 2.731401E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.845 | TFLOPs: 42.32 | +7: iteration 2940/ 7508 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.58 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 2.740961E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.701 | TFLOPs: 41.73 | +7: iteration 2950/ 7508 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.59 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 2.734775E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.642 | TFLOPs: 41.25 | +7: iteration 2960/ 7508 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.57 | learning rate: 1.410E-04 | global batch size: 256 | lm loss: 2.787402E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.272 | TFLOPs: 42.64 | +7: iteration 2970/ 7508 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.58 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 2.794289E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.489 | TFLOPs: 41.81 | +7: iteration 2980/ 7508 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.59 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 2.768443E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.212 | TFLOPs: 41.40 | +7: iteration 2990/ 7508 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.58 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 2.757609E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.031 | TFLOPs: 41.76 | +7: iteration 3000/ 7508 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.60 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 2.760478E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.277 | TFLOPs: 40.45 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 3000 | lm loss value: 2.703434E+00 | lm loss PPL: 1.493091E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 3000 to checkpoints_421m +0: [2022-11-25 18:17:10,608] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +0: [2022-11-25 18:17:10,611] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_01-model_00-model_states.pt... +0: [2022-11-25 18:17:10,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_01-model_00-model_states.pt. +0: [2022-11-25 18:17:10,752] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_03-model_00-model_states.pt... +0: [2022-11-25 18:17:10,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_03-model_00-model_states.pt. +0: [2022-11-25 18:17:10,792] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_04-model_00-model_states.pt... +0: [2022-11-25 18:17:10,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_04-model_00-model_states.pt. +0: [2022-11-25 18:17:10,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_05-model_00-model_states.pt... +0: [2022-11-25 18:17:10,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_05-model_00-model_states.pt. +0: [2022-11-25 18:17:10,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_06-model_00-model_states.pt... +0: [2022-11-25 18:17:10,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_06-model_00-model_states.pt. +0: [2022-11-25 18:17:10,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_07-model_00-model_states.pt... +0: [2022-11-25 18:17:10,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_07-model_00-model_states.pt. +0: [2022-11-25 18:17:10,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_08-model_00-model_states.pt... +0: [2022-11-25 18:17:10,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_08-model_00-model_states.pt. +0: [2022-11-25 18:17:10,993] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_09-model_00-model_states.pt... +0: [2022-11-25 18:17:11,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_09-model_00-model_states.pt. +0: [2022-11-25 18:17:11,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_10-model_00-model_states.pt... +0: [2022-11-25 18:17:11,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_10-model_00-model_states.pt. +0: [2022-11-25 18:17:11,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_11-model_00-model_states.pt... +0: [2022-11-25 18:17:11,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_11-model_00-model_states.pt. +0: [2022-11-25 18:17:11,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_12-model_00-model_states.pt... +0: [2022-11-25 18:17:11,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_12-model_00-model_states.pt. +0: [2022-11-25 18:17:11,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_13-model_00-model_states.pt... +0: [2022-11-25 18:17:11,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_13-model_00-model_states.pt. +0: [2022-11-25 18:17:11,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_14-model_00-model_states.pt... +0: [2022-11-25 18:17:11,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_14-model_00-model_states.pt. +0: [2022-11-25 18:17:11,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_15-model_00-model_states.pt... +0: [2022-11-25 18:17:11,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_15-model_00-model_states.pt. +0: [2022-11-25 18:17:11,270] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_16-model_00-model_states.pt... +0: [2022-11-25 18:17:11,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_16-model_00-model_states.pt. +0: [2022-11-25 18:17:11,310] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_17-model_00-model_states.pt... +0: [2022-11-25 18:17:11,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_17-model_00-model_states.pt. +0: [2022-11-25 18:17:11,350] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_18-model_00-model_states.pt... +0: [2022-11-25 18:17:11,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_18-model_00-model_states.pt. +0: [2022-11-25 18:17:11,390] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_19-model_00-model_states.pt... +0: [2022-11-25 18:17:11,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_19-model_00-model_states.pt. +0: [2022-11-25 18:17:11,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_20-model_00-model_states.pt... +0: [2022-11-25 18:17:11,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_20-model_00-model_states.pt. +0: [2022-11-25 18:17:11,479] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/layer_22-model_00-model_states.pt... +0: [2022-11-25 18:17:11,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/layer_22-model_00-model_states.pt. +0: [2022-11-25 18:17:11,484] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step3000/mp_rank_00_model_states.pt +0: [2022-11-25 18:17:11,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/mp_rank_00_model_states.pt... +0: [2022-11-25 18:17:11,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/mp_rank_00_model_states.pt. +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:17:11,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:17:11,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:17:11,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-25 18:17:11,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-25 18:17:11,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:17:11,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:17:11,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:17:11,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:17:11,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:17:11,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 18:17:11,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +3: [2022-11-25 18:17:11,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:17:11,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:17:11,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:17:11,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:17:11,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:17:11,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:17:11,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: [2022-11-25 18:17:11,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-25 18:17:11,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +4: [2022-11-25 18:17:11,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:17:11,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 18:17:11,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +5: [2022-11-25 18:17:11,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:17:11,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 18:17:11,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +6: [2022-11-25 18:17:11,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:17:11,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 18:17:11,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +1: [2022-11-25 18:17:11,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:17:11,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 18:17:11,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +7: [2022-11-25 18:17:11,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:17:11,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 18:17:11,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:17:11,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 18:17:11,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +2: [2022-11-25 18:17:11,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-25 18:17:11,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +0: successfully saved checkpoint at iteration 3000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1110.42 +7: iteration 3010/ 7508 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.71 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 2.741113E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 362.773 | TFLOPs: 34.59 | +7: iteration 3020/ 7508 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.57 | learning rate: 1.388E-04 | global batch size: 256 | lm loss: 2.759577E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.994 | TFLOPs: 42.52 | +7: iteration 3030/ 7508 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.58 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 2.715633E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.518 | TFLOPs: 41.81 | +7: iteration 3040/ 7508 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.59 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 2.756859E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.797 | TFLOPs: 41.07 | +7: iteration 3050/ 7508 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.59 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 2.763709E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.550 | TFLOPs: 41.62 | +7: iteration 3060/ 7508 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.60 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 2.781494E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.866 | TFLOPs: 40.51 | +7: iteration 3070/ 7508 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.59 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 2.782589E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.204 | TFLOPs: 41.30 | +7: iteration 3080/ 7508 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.59 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 2.750388E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.287 | TFLOPs: 41.40 | +7: iteration 3090/ 7508 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.58 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 2.749836E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.079 | TFLOPs: 41.86 | +7: iteration 3100/ 7508 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.59 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 2.777606E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.910 | TFLOPs: 41.65 | +7: iteration 3110/ 7508 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.60 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 2.713132E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.866 | TFLOPs: 40.70 | +7: iteration 3120/ 7508 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.57 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 2.755127E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.871 | TFLOPs: 42.89 | +7: iteration 3130/ 7508 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.58 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 2.749611E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.057 | TFLOPs: 42.24 | +7: iteration 3140/ 7508 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.58 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 2.719460E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.009 | TFLOPs: 42.33 | +7: iteration 3150/ 7508 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.57 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 2.761289E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.553 | TFLOPs: 42.48 | +7: iteration 3160/ 7508 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.60 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 2.713614E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.913 | TFLOPs: 40.51 | +7: iteration 3170/ 7508 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.57 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 2.726955E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.121 | TFLOPs: 42.82 | +7: iteration 3180/ 7508 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.57 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 2.746350E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.902 | TFLOPs: 42.51 | +7: iteration 3190/ 7508 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.59 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 2.703050E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.952 | TFLOPs: 41.66 | +7: iteration 3200/ 7508 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.56 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 2.710856E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.566 | TFLOPs: 43.34 | +7: iteration 3210/ 7508 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.58 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 2.759199E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.743 | TFLOPs: 41.73 | +7: iteration 3220/ 7508 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.57 | learning rate: 1.315E-04 | global batch size: 256 | lm loss: 2.719892E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.818 | TFLOPs: 43.17 | +7: iteration 3230/ 7508 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.57 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 2.745014E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.407 | TFLOPs: 42.75 | +7: iteration 3240/ 7508 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.58 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 2.718943E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.769 | TFLOPs: 42.12 | +7: iteration 3250/ 7508 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.58 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 2.697709E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.792 | TFLOPs: 42.31 | +7: iteration 3260/ 7508 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.57 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 2.730347E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.526 | TFLOPs: 42.48 | +7: iteration 3270/ 7508 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.59 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 2.735306E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.978 | TFLOPs: 41.57 | +7: iteration 3280/ 7508 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.59 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 2.721971E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.304 | TFLOPs: 41.69 | +7: iteration 3290/ 7508 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.57 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 2.695408E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.290 | TFLOPs: 42.64 | +7: iteration 3300/ 7508 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.59 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 2.764687E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.244 | TFLOPs: 41.21 | +7: iteration 3310/ 7508 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.57 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 2.734735E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.479 | TFLOPs: 43.14 | +7: iteration 3320/ 7508 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.59 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 2.746147E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.807 | TFLOPs: 41.45 | +7: iteration 3330/ 7508 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.57 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 2.757261E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.903 | TFLOPs: 42.51 | +7: iteration 3340/ 7508 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.58 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 2.749216E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.870 | TFLOPs: 42.22 | +7: iteration 3350/ 7508 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.57 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 2.736899E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.776 | TFLOPs: 42.98 | +7: iteration 3360/ 7508 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.59 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 2.724865E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.240 | TFLOPs: 41.40 | +7: iteration 3370/ 7508 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.58 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 2.746044E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.859 | TFLOPs: 42.41 | +7: iteration 3380/ 7508 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.58 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 2.727151E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.039 | TFLOPs: 41.95 | +7: iteration 3390/ 7508 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.58 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 2.723041E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.854 | TFLOPs: 41.94 | +7: iteration 3400/ 7508 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.58 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 2.696563E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.129 | TFLOPs: 42.06 | +7: iteration 3410/ 7508 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.59 | learning rate: 1.245E-04 | global batch size: 256 | lm loss: 2.758764E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.203 | TFLOPs: 41.40 | +7: iteration 3420/ 7508 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.58 | learning rate: 1.241E-04 | global batch size: 256 | lm loss: 2.743402E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.495 | TFLOPs: 42.19 | +7: iteration 3430/ 7508 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.56 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 2.700131E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.704 | TFLOPs: 43.45 | +7: iteration 3440/ 7508 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.58 | learning rate: 1.233E-04 | global batch size: 256 | lm loss: 2.673427E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.931 | TFLOPs: 41.85 | +7: iteration 3450/ 7508 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.58 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 2.738548E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.415 | TFLOPs: 41.99 | +7: iteration 3460/ 7508 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.57 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 2.709883E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.816 | TFLOPs: 42.69 | +7: iteration 3470/ 7508 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.58 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 2.738728E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.022 | TFLOPs: 42.14 | +7: iteration 3480/ 7508 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.57 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 2.726865E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.057 | TFLOPs: 42.72 | +7: iteration 3490/ 7508 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.57 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 2.697943E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.529 | TFLOPs: 42.67 | +7: iteration 3500/ 7508 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.58 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 2.696990E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.987 | TFLOPs: 42.04 | +7: iteration 3510/ 7508 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.60 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 2.712346E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 423.550 | TFLOPs: 40.38 | +7: iteration 3520/ 7508 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.60 | learning rate: 1.203E-04 | global batch size: 256 | lm loss: 2.689152E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.247 | TFLOPs: 40.73 | +7: iteration 3530/ 7508 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.58 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 2.703339E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.539 | TFLOPs: 42.10 | +7: iteration 3540/ 7508 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.59 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 2.727127E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.418 | TFLOPs: 41.51 | +7: iteration 3550/ 7508 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.58 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 2.710247E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.549 | TFLOPs: 42.10 | +7: iteration 3560/ 7508 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.58 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 2.731593E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.223 | TFLOPs: 42.26 | +7: iteration 3570/ 7508 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.58 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 2.715234E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.352 | TFLOPs: 41.79 | +7: iteration 3580/ 7508 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.58 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 2.727849E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.438 | TFLOPs: 42.18 | +7: iteration 3590/ 7508 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.58 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 2.682994E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.068 | TFLOPs: 41.86 | +7: iteration 3600/ 7508 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.58 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 2.698860E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.763 | TFLOPs: 41.83 | +7: iteration 3610/ 7508 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.57 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 2.721483E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.747 | TFLOPs: 43.16 | +7: iteration 3620/ 7508 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.56 | learning rate: 1.165E-04 | global batch size: 256 | lm loss: 2.686609E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.504 | TFLOPs: 43.33 | +7: iteration 3630/ 7508 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.57 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 2.718578E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.686 | TFLOPs: 42.59 | +7: iteration 3640/ 7508 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.58 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 2.729809E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.986 | TFLOPs: 42.23 | +7: iteration 3650/ 7508 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.57 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 2.688385E+00 | grad norm: 0.489 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.461 | TFLOPs: 42.95 | +7: iteration 3660/ 7508 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.57 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 2.718023E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.366 | TFLOPs: 43.03 | +7: iteration 3670/ 7508 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.60 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 2.777325E+00 | grad norm: 0.857 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.422 | TFLOPs: 40.65 | +7: iteration 3680/ 7508 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.57 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 2.806489E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.443 | TFLOPs: 42.85 | +7: iteration 3690/ 7508 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.58 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 2.757178E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.127 | TFLOPs: 42.06 | +7: iteration 3700/ 7508 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.57 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 2.717941E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.895 | TFLOPs: 42.61 | +7: iteration 3710/ 7508 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.58 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 2.716667E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.495 | TFLOPs: 42.38 | +7: iteration 3720/ 7508 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.58 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 2.725265E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.625 | TFLOPs: 42.01 | +7: iteration 3730/ 7508 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.58 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 2.714135E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.446 | TFLOPs: 42.37 | +7: iteration 3740/ 7508 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.57 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 2.692810E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.290 | TFLOPs: 42.83 | +7: iteration 3750/ 7508 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.57 | learning rate: 1.116E-04 | global batch size: 256 | lm loss: 2.724516E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.870 | TFLOPs: 42.60 | +7: iteration 3760/ 7508 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.57 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 2.673982E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.533 | TFLOPs: 42.57 | +7: iteration 3770/ 7508 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.58 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 2.700959E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.521 | TFLOPs: 41.90 | +7: iteration 3780/ 7508 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.57 | learning rate: 1.104E-04 | global batch size: 256 | lm loss: 2.696267E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.399 | TFLOPs: 42.56 | +7: iteration 3790/ 7508 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.59 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 2.705940E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.952 | TFLOPs: 41.09 | +7: iteration 3800/ 7508 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.58 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 2.706047E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.468 | TFLOPs: 42.09 | +7: iteration 3810/ 7508 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.58 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 2.694577E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.590 | TFLOPs: 41.81 | +7: iteration 3820/ 7508 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.58 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 2.708611E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.227 | TFLOPs: 42.07 | +7: iteration 3830/ 7508 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.59 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 2.723851E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.497 | TFLOPs: 41.52 | +7: iteration 3840/ 7508 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.58 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 2.690181E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.826 | TFLOPs: 42.41 | +7: iteration 3850/ 7508 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.56 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 2.664287E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.424 | TFLOPs: 43.61 | +7: iteration 3860/ 7508 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.60 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 2.682671E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.483 | TFLOPs: 40.66 | +7: iteration 3870/ 7508 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.57 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 2.652030E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.956 | TFLOPs: 42.52 | +7: iteration 3880/ 7508 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.60 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 2.704814E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.479 | TFLOPs: 40.95 | +7: iteration 3890/ 7508 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.58 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 2.705376E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.156 | TFLOPs: 42.15 | +7: iteration 3900/ 7508 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.57 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 2.666837E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.977 | TFLOPs: 42.71 | +7: iteration 3910/ 7508 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.57 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 2.687263E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.211 | TFLOPs: 42.92 | +7: iteration 3920/ 7508 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.56 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 2.672166E+00 | grad norm: 0.467 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.265 | TFLOPs: 43.31 | +7: iteration 3930/ 7508 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.57 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 2.716503E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.793 | TFLOPs: 42.60 | +7: iteration 3940/ 7508 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.56 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 2.651939E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.599 | TFLOPs: 43.34 | +7: iteration 3950/ 7508 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.57 | learning rate: 1.040E-04 | global batch size: 256 | lm loss: 2.676762E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.269 | TFLOPs: 42.55 | +7: iteration 3960/ 7508 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.60 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 2.648403E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 424.185 | TFLOPs: 40.44 | +7: iteration 3970/ 7508 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.57 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 2.709196E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.745 | TFLOPs: 42.69 | +7: iteration 3980/ 7508 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.61 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 2.686129E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.572 | TFLOPs: 40.29 | +7: iteration 3990/ 7508 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.59 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 2.701493E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.887 | TFLOPs: 41.65 | +0: [2022-11-25 18:26:51,342] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00010208850566272403, 0.00010208850566272403, 0.00010208850566272403], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 4000/ 7508 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.57 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 2.658109E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.092 | TFLOPs: 42.82 | +0: steps: 4000 loss: 2.6172 iter time (s): 0.578 samples/sec: 443.278 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 4000 | lm loss value: 2.739674E+00 | lm loss PPL: 1.548194E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 4000 to checkpoints_421m +0: [2022-11-25 18:26:51,547] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! +0: [2022-11-25 18:26:51,552] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_01-model_00-model_states.pt... +0: [2022-11-25 18:26:51,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_01-model_00-model_states.pt. +0: [2022-11-25 18:26:51,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_03-model_00-model_states.pt... +0: [2022-11-25 18:26:51,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_03-model_00-model_states.pt. +0: [2022-11-25 18:26:51,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_04-model_00-model_states.pt... +0: [2022-11-25 18:26:51,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_04-model_00-model_states.pt. +0: [2022-11-25 18:26:51,771] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_05-model_00-model_states.pt... +0: [2022-11-25 18:26:51,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_05-model_00-model_states.pt. +0: [2022-11-25 18:26:51,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_06-model_00-model_states.pt... +0: [2022-11-25 18:26:51,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_06-model_00-model_states.pt. +0: [2022-11-25 18:26:51,851] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_07-model_00-model_states.pt... +0: [2022-11-25 18:26:51,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_07-model_00-model_states.pt. +0: [2022-11-25 18:26:51,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_08-model_00-model_states.pt... +0: [2022-11-25 18:26:51,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_08-model_00-model_states.pt. +0: [2022-11-25 18:26:51,930] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_09-model_00-model_states.pt... +0: [2022-11-25 18:26:51,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_09-model_00-model_states.pt. +0: [2022-11-25 18:26:51,970] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_10-model_00-model_states.pt... +0: [2022-11-25 18:26:52,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_10-model_00-model_states.pt. +0: [2022-11-25 18:26:52,010] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_11-model_00-model_states.pt... +0: [2022-11-25 18:26:52,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_11-model_00-model_states.pt. +0: [2022-11-25 18:26:52,050] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_12-model_00-model_states.pt... +0: [2022-11-25 18:26:52,089] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_12-model_00-model_states.pt. +0: [2022-11-25 18:26:52,090] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_13-model_00-model_states.pt... +0: [2022-11-25 18:26:52,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_13-model_00-model_states.pt. +0: [2022-11-25 18:26:52,129] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_14-model_00-model_states.pt... +0: [2022-11-25 18:26:52,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_14-model_00-model_states.pt. +0: [2022-11-25 18:26:52,169] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_15-model_00-model_states.pt... +0: [2022-11-25 18:26:52,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_15-model_00-model_states.pt. +0: [2022-11-25 18:26:52,210] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_16-model_00-model_states.pt... +0: [2022-11-25 18:26:52,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_16-model_00-model_states.pt. +0: [2022-11-25 18:26:52,250] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_17-model_00-model_states.pt... +0: [2022-11-25 18:26:52,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_17-model_00-model_states.pt. +0: [2022-11-25 18:26:52,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_18-model_00-model_states.pt... +0: [2022-11-25 18:26:52,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_18-model_00-model_states.pt. +0: [2022-11-25 18:26:52,329] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_19-model_00-model_states.pt... +0: [2022-11-25 18:26:52,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_19-model_00-model_states.pt. +0: [2022-11-25 18:26:52,368] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_20-model_00-model_states.pt... +0: [2022-11-25 18:26:52,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_20-model_00-model_states.pt. +0: [2022-11-25 18:26:52,411] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/layer_22-model_00-model_states.pt... +0: [2022-11-25 18:26:52,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/layer_22-model_00-model_states.pt. +0: [2022-11-25 18:26:52,413] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step4000/mp_rank_00_model_states.pt +0: [2022-11-25 18:26:52,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/mp_rank_00_model_states.pt... +0: [2022-11-25 18:26:52,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/mp_rank_00_model_states.pt. +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:26:52,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,522] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,522] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-25 18:26:52,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:26:52,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:26:52,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-25 18:26:52,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-25 18:26:52,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:26:52,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +5: [2022-11-25 18:26:52,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:26:52,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +3: [2022-11-25 18:26:52,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:26:52,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-25 18:26:52,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:26:52,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +1: [2022-11-25 18:26:52,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +6: [2022-11-25 18:26:52,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:26:52,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +6: [2022-11-25 18:26:52,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:26:52,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:26:52,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 18:26:52,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +2: [2022-11-25 18:26:52,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:26:52,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 18:26:52,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +4: [2022-11-25 18:26:52,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:26:52,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 18:26:52,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +7: [2022-11-25 18:26:52,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:26:52,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 18:26:52,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:26:52,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: [2022-11-25 18:26:52,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 18:26:52,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +0: successfully saved checkpoint at iteration 4000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1105.01 +7: iteration 4010/ 7508 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.70 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 2.667000E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 364.509 | TFLOPs: 34.75 | +7: iteration 4020/ 7508 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.57 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 2.699218E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.703 | TFLOPs: 42.59 | +7: iteration 4030/ 7508 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.61 | learning rate: 1.010E-04 | global batch size: 256 | lm loss: 2.667571E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 419.463 | TFLOPs: 39.99 | +7: iteration 4040/ 7508 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.59 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 2.641497E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.414 | TFLOPs: 41.23 | +7: iteration 4050/ 7508 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.57 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 2.651528E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.740 | TFLOPs: 42.59 | +7: iteration 4060/ 7508 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.60 | learning rate: 9.982E-05 | global batch size: 256 | lm loss: 2.690496E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.562 | TFLOPs: 40.95 | +7: iteration 4070/ 7508 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.58 | learning rate: 9.944E-05 | global batch size: 256 | lm loss: 2.699595E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.153 | TFLOPs: 42.15 | +7: iteration 4080/ 7508 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.59 | learning rate: 9.906E-05 | global batch size: 256 | lm loss: 2.669133E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.287 | TFLOPs: 41.40 | +7: iteration 4090/ 7508 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.60 | learning rate: 9.868E-05 | global batch size: 256 | lm loss: 2.678064E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.590 | TFLOPs: 40.77 | +7: iteration 4100/ 7508 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.57 | learning rate: 9.831E-05 | global batch size: 256 | lm loss: 2.669506E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.641 | TFLOPs: 42.49 | +7: iteration 4110/ 7508 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.58 | learning rate: 9.793E-05 | global batch size: 256 | lm loss: 2.634909E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.663 | TFLOPs: 42.30 | +7: iteration 4120/ 7508 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.58 | learning rate: 9.755E-05 | global batch size: 256 | lm loss: 2.629039E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.873 | TFLOPs: 41.84 | +7: iteration 4130/ 7508 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.58 | learning rate: 9.718E-05 | global batch size: 256 | lm loss: 2.634964E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.362 | TFLOPs: 42.17 | +7: iteration 4140/ 7508 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.59 | learning rate: 9.680E-05 | global batch size: 256 | lm loss: 2.652077E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.802 | TFLOPs: 41.45 | +7: iteration 4150/ 7508 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.58 | learning rate: 9.642E-05 | global batch size: 256 | lm loss: 2.665486E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.835 | TFLOPs: 42.12 | +7: iteration 4160/ 7508 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.58 | learning rate: 9.605E-05 | global batch size: 256 | lm loss: 2.665706E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.667 | TFLOPs: 41.73 | +7: iteration 4170/ 7508 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.58 | learning rate: 9.567E-05 | global batch size: 256 | lm loss: 2.640114E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.080 | TFLOPs: 42.15 | +7: iteration 4180/ 7508 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.59 | learning rate: 9.530E-05 | global batch size: 256 | lm loss: 2.659671E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.576 | TFLOPs: 41.53 | +7: iteration 4190/ 7508 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.59 | learning rate: 9.492E-05 | global batch size: 256 | lm loss: 2.626571E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.608 | TFLOPs: 41.05 | +7: iteration 4200/ 7508 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.59 | learning rate: 9.455E-05 | global batch size: 256 | lm loss: 2.660925E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.878 | TFLOPs: 41.56 | +7: iteration 4210/ 7508 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.58 | learning rate: 9.417E-05 | global batch size: 256 | lm loss: 2.657724E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.947 | TFLOPs: 42.33 | +7: iteration 4220/ 7508 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.58 | learning rate: 9.380E-05 | global batch size: 256 | lm loss: 2.677342E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.310 | TFLOPs: 42.26 | +7: iteration 4230/ 7508 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.57 | learning rate: 9.342E-05 | global batch size: 256 | lm loss: 2.657124E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.668 | TFLOPs: 42.49 | +7: iteration 4240/ 7508 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.58 | learning rate: 9.305E-05 | global batch size: 256 | lm loss: 2.656328E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.711 | TFLOPs: 42.40 | +7: iteration 4250/ 7508 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.59 | learning rate: 9.268E-05 | global batch size: 256 | lm loss: 2.636642E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.518 | TFLOPs: 41.33 | +7: iteration 4260/ 7508 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.59 | learning rate: 9.230E-05 | global batch size: 256 | lm loss: 2.662791E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.667 | TFLOPs: 41.44 | +7: iteration 4270/ 7508 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.59 | learning rate: 9.193E-05 | global batch size: 256 | lm loss: 2.619631E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.797 | TFLOPs: 41.55 | +7: iteration 4280/ 7508 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.59 | learning rate: 9.156E-05 | global batch size: 256 | lm loss: 2.658090E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.166 | TFLOPs: 41.68 | +7: iteration 4290/ 7508 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.58 | learning rate: 9.119E-05 | global batch size: 256 | lm loss: 2.644299E+00 | grad norm: 0.938 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.503 | TFLOPs: 41.90 | +7: iteration 4300/ 7508 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.57 | learning rate: 9.082E-05 | global batch size: 256 | lm loss: 2.663572E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.251 | TFLOPs: 43.12 | +7: iteration 4310/ 7508 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.57 | learning rate: 9.044E-05 | global batch size: 256 | lm loss: 2.652467E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.905 | TFLOPs: 42.80 | +7: iteration 4320/ 7508 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.57 | learning rate: 9.007E-05 | global batch size: 256 | lm loss: 2.648980E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.385 | TFLOPs: 42.75 | +7: iteration 4330/ 7508 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.59 | learning rate: 8.970E-05 | global batch size: 256 | lm loss: 2.622632E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.579 | TFLOPs: 41.24 | +7: iteration 4340/ 7508 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.58 | learning rate: 8.933E-05 | global batch size: 256 | lm loss: 2.684042E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.644 | TFLOPs: 42.20 | +7: iteration 4350/ 7508 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.57 | learning rate: 8.896E-05 | global batch size: 256 | lm loss: 2.653899E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.803 | TFLOPs: 42.50 | +7: iteration 4360/ 7508 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.58 | learning rate: 8.859E-05 | global batch size: 256 | lm loss: 2.647190E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.628 | TFLOPs: 41.82 | +7: iteration 4370/ 7508 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.56 | learning rate: 8.822E-05 | global batch size: 256 | lm loss: 2.680924E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.995 | TFLOPs: 43.47 | +7: iteration 4380/ 7508 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.59 | learning rate: 8.785E-05 | global batch size: 256 | lm loss: 2.644192E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.419 | TFLOPs: 41.04 | +7: iteration 4390/ 7508 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.58 | learning rate: 8.749E-05 | global batch size: 256 | lm loss: 2.675113E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.394 | TFLOPs: 41.89 | +7: iteration 4400/ 7508 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.58 | learning rate: 8.712E-05 | global batch size: 256 | lm loss: 2.654037E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.472 | TFLOPs: 42.28 | +7: iteration 4410/ 7508 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.58 | learning rate: 8.675E-05 | global batch size: 256 | lm loss: 2.629054E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.039 | TFLOPs: 42.43 | +7: iteration 4420/ 7508 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.58 | learning rate: 8.638E-05 | global batch size: 256 | lm loss: 2.640509E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.292 | TFLOPs: 42.26 | +7: iteration 4430/ 7508 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.58 | learning rate: 8.602E-05 | global batch size: 256 | lm loss: 2.615381E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.432 | TFLOPs: 42.37 | +7: iteration 4440/ 7508 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.58 | learning rate: 8.565E-05 | global batch size: 256 | lm loss: 2.652755E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.623 | TFLOPs: 42.20 | +7: iteration 4450/ 7508 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.58 | learning rate: 8.528E-05 | global batch size: 256 | lm loss: 2.655861E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.290 | TFLOPs: 42.26 | +7: iteration 4460/ 7508 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.57 | learning rate: 8.492E-05 | global batch size: 256 | lm loss: 2.591514E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.335 | TFLOPs: 42.93 | +7: iteration 4470/ 7508 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.57 | learning rate: 8.455E-05 | global batch size: 256 | lm loss: 2.631996E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.116 | TFLOPs: 42.53 | +7: iteration 4480/ 7508 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.57 | learning rate: 8.419E-05 | global batch size: 256 | lm loss: 2.651304E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.613 | TFLOPs: 43.06 | +7: iteration 4490/ 7508 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.56 | learning rate: 8.382E-05 | global batch size: 256 | lm loss: 2.605959E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.797 | TFLOPs: 43.65 | +7: iteration 4500/ 7508 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.57 | learning rate: 8.346E-05 | global batch size: 256 | lm loss: 2.637831E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.841 | TFLOPs: 42.79 | +7: iteration 4510/ 7508 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.58 | learning rate: 8.310E-05 | global batch size: 256 | lm loss: 2.619205E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.323 | TFLOPs: 42.36 | +7: iteration 4520/ 7508 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.58 | learning rate: 8.273E-05 | global batch size: 256 | lm loss: 2.642379E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.382 | TFLOPs: 42.37 | +7: iteration 4530/ 7508 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.59 | learning rate: 8.237E-05 | global batch size: 256 | lm loss: 2.666148E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.576 | TFLOPs: 41.62 | +7: iteration 4540/ 7508 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.58 | learning rate: 8.201E-05 | global batch size: 256 | lm loss: 2.645969E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.073 | TFLOPs: 42.24 | +7: iteration 4550/ 7508 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.56 | learning rate: 8.165E-05 | global batch size: 256 | lm loss: 2.619892E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.326 | TFLOPs: 43.32 | +7: iteration 4560/ 7508 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.57 | learning rate: 8.129E-05 | global batch size: 256 | lm loss: 2.636189E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.547 | TFLOPs: 42.86 | +7: iteration 4570/ 7508 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.57 | learning rate: 8.093E-05 | global batch size: 256 | lm loss: 2.622494E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.485 | TFLOPs: 42.57 | +7: iteration 4580/ 7508 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.58 | learning rate: 8.057E-05 | global batch size: 256 | lm loss: 2.643105E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.939 | TFLOPs: 42.32 | +7: iteration 4590/ 7508 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.57 | learning rate: 8.021E-05 | global batch size: 256 | lm loss: 2.596626E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.217 | TFLOPs: 42.54 | +7: iteration 4600/ 7508 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.58 | learning rate: 7.985E-05 | global batch size: 256 | lm loss: 2.661915E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.564 | TFLOPs: 42.19 | +7: iteration 4610/ 7508 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.58 | learning rate: 7.949E-05 | global batch size: 256 | lm loss: 2.630916E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.734 | TFLOPs: 42.40 | +7: iteration 4620/ 7508 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.58 | learning rate: 7.913E-05 | global batch size: 256 | lm loss: 2.637238E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.485 | TFLOPs: 42.38 | +7: iteration 4630/ 7508 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.59 | learning rate: 7.878E-05 | global batch size: 256 | lm loss: 2.653483E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.980 | TFLOPs: 41.57 | +7: iteration 4640/ 7508 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.59 | learning rate: 7.842E-05 | global batch size: 256 | lm loss: 2.664408E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.533 | TFLOPs: 41.71 | +7: iteration 4650/ 7508 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.57 | learning rate: 7.807E-05 | global batch size: 256 | lm loss: 2.624490E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.595 | TFLOPs: 42.67 | +7: iteration 4660/ 7508 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.58 | learning rate: 7.771E-05 | global batch size: 256 | lm loss: 2.622354E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.349 | TFLOPs: 41.89 | +7: iteration 4670/ 7508 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.57 | learning rate: 7.736E-05 | global batch size: 256 | lm loss: 2.603422E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.409 | TFLOPs: 42.56 | +7: iteration 4680/ 7508 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.57 | learning rate: 7.700E-05 | global batch size: 256 | lm loss: 2.621047E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.631 | TFLOPs: 43.06 | +7: iteration 4690/ 7508 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.58 | learning rate: 7.665E-05 | global batch size: 256 | lm loss: 2.645311E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.680 | TFLOPs: 42.11 | +7: iteration 4700/ 7508 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.58 | learning rate: 7.629E-05 | global batch size: 256 | lm loss: 2.628720E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.049 | TFLOPs: 42.34 | +7: iteration 4710/ 7508 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.58 | learning rate: 7.594E-05 | global batch size: 256 | lm loss: 2.605730E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.297 | TFLOPs: 42.36 | +7: iteration 4720/ 7508 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.58 | learning rate: 7.559E-05 | global batch size: 256 | lm loss: 2.625377E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.859 | TFLOPs: 41.75 | +7: iteration 4730/ 7508 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.58 | learning rate: 7.524E-05 | global batch size: 256 | lm loss: 2.599465E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.205 | TFLOPs: 41.87 | +7: iteration 4740/ 7508 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.57 | learning rate: 7.489E-05 | global batch size: 256 | lm loss: 2.623374E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.245 | TFLOPs: 42.64 | +7: iteration 4750/ 7508 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.58 | learning rate: 7.454E-05 | global batch size: 256 | lm loss: 2.616648E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.629 | TFLOPs: 41.82 | +7: iteration 4760/ 7508 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.57 | learning rate: 7.419E-05 | global batch size: 256 | lm loss: 2.623471E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.271 | TFLOPs: 43.02 | +7: iteration 4770/ 7508 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.57 | learning rate: 7.384E-05 | global batch size: 256 | lm loss: 2.651262E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.420 | TFLOPs: 42.56 | +7: iteration 4780/ 7508 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.58 | learning rate: 7.349E-05 | global batch size: 256 | lm loss: 2.607052E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.770 | TFLOPs: 42.12 | +7: iteration 4790/ 7508 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.57 | learning rate: 7.315E-05 | global batch size: 256 | lm loss: 2.628834E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.242 | TFLOPs: 42.45 | +7: iteration 4800/ 7508 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.57 | learning rate: 7.280E-05 | global batch size: 256 | lm loss: 2.643594E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.382 | TFLOPs: 42.65 | +7: iteration 4810/ 7508 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.57 | learning rate: 7.245E-05 | global batch size: 256 | lm loss: 2.629368E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.248 | TFLOPs: 42.45 | +7: iteration 4820/ 7508 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.58 | learning rate: 7.211E-05 | global batch size: 256 | lm loss: 2.613602E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.897 | TFLOPs: 41.75 | +7: iteration 4830/ 7508 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.57 | learning rate: 7.176E-05 | global batch size: 256 | lm loss: 2.603307E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.436 | TFLOPs: 42.85 | +7: iteration 4840/ 7508 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.58 | learning rate: 7.142E-05 | global batch size: 256 | lm loss: 2.579222E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.845 | TFLOPs: 41.84 | +7: iteration 4850/ 7508 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.57 | learning rate: 7.108E-05 | global batch size: 256 | lm loss: 2.613574E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.047 | TFLOPs: 43.00 | +7: iteration 4860/ 7508 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.58 | learning rate: 7.073E-05 | global batch size: 256 | lm loss: 2.645923E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.199 | TFLOPs: 42.35 | +7: iteration 4870/ 7508 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.58 | learning rate: 7.039E-05 | global batch size: 256 | lm loss: 2.603652E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.875 | TFLOPs: 42.13 | +7: iteration 4880/ 7508 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.57 | learning rate: 7.005E-05 | global batch size: 256 | lm loss: 2.647278E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.083 | TFLOPs: 42.91 | +7: iteration 4890/ 7508 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.57 | learning rate: 6.971E-05 | global batch size: 256 | lm loss: 2.621980E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.363 | TFLOPs: 42.46 | +7: iteration 4900/ 7508 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.60 | learning rate: 6.937E-05 | global batch size: 256 | lm loss: 2.595547E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.992 | TFLOPs: 40.80 | +7: iteration 4910/ 7508 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.58 | learning rate: 6.903E-05 | global batch size: 256 | lm loss: 2.583937E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.105 | TFLOPs: 42.34 | +7: iteration 4920/ 7508 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.58 | learning rate: 6.869E-05 | global batch size: 256 | lm loss: 2.631274E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.123 | TFLOPs: 42.25 | +7: iteration 4930/ 7508 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.58 | learning rate: 6.835E-05 | global batch size: 256 | lm loss: 2.606921E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.128 | TFLOPs: 42.44 | +7: iteration 4940/ 7508 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.58 | learning rate: 6.802E-05 | global batch size: 256 | lm loss: 2.618509E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.411 | TFLOPs: 41.89 | +7: iteration 4950/ 7508 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.59 | learning rate: 6.768E-05 | global batch size: 256 | lm loss: 2.642247E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.683 | TFLOPs: 41.54 | +7: iteration 4960/ 7508 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.59 | learning rate: 6.735E-05 | global batch size: 256 | lm loss: 2.611109E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.232 | TFLOPs: 41.59 | +7: iteration 4970/ 7508 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.57 | learning rate: 6.701E-05 | global batch size: 256 | lm loss: 2.605125E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.550 | TFLOPs: 42.76 | +7: iteration 4980/ 7508 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.58 | learning rate: 6.668E-05 | global batch size: 256 | lm loss: 2.620416E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.650 | TFLOPs: 42.01 | +7: iteration 4990/ 7508 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.58 | learning rate: 6.634E-05 | global batch size: 256 | lm loss: 2.597829E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.742 | TFLOPs: 42.31 | +7: iteration 5000/ 7508 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.58 | learning rate: 6.601E-05 | global batch size: 256 | lm loss: 2.593642E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.382 | TFLOPs: 42.27 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 5000 | lm loss value: 2.619111E+00 | lm loss PPL: 1.372352E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 5000 to checkpoints_421m +0: [2022-11-25 18:36:31,605] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! +0: [2022-11-25 18:36:31,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_01-model_00-model_states.pt... +0: [2022-11-25 18:36:31,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_01-model_00-model_states.pt. +0: [2022-11-25 18:36:31,748] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_03-model_00-model_states.pt... +0: [2022-11-25 18:36:31,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_03-model_00-model_states.pt. +0: [2022-11-25 18:36:31,788] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_04-model_00-model_states.pt... +0: [2022-11-25 18:36:31,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_04-model_00-model_states.pt. +0: [2022-11-25 18:36:31,828] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_05-model_00-model_states.pt... +0: [2022-11-25 18:36:31,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_05-model_00-model_states.pt. +0: [2022-11-25 18:36:31,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_06-model_00-model_states.pt... +0: [2022-11-25 18:36:31,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_06-model_00-model_states.pt. +0: [2022-11-25 18:36:31,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_07-model_00-model_states.pt... +0: [2022-11-25 18:36:31,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_07-model_00-model_states.pt. +0: [2022-11-25 18:36:31,949] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_08-model_00-model_states.pt... +0: [2022-11-25 18:36:31,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_08-model_00-model_states.pt. +0: [2022-11-25 18:36:31,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_09-model_00-model_states.pt... +0: [2022-11-25 18:36:32,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_09-model_00-model_states.pt. +0: [2022-11-25 18:36:32,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_10-model_00-model_states.pt... +0: [2022-11-25 18:36:32,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_10-model_00-model_states.pt. +0: [2022-11-25 18:36:32,069] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_11-model_00-model_states.pt... +0: [2022-11-25 18:36:32,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_11-model_00-model_states.pt. +0: [2022-11-25 18:36:32,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_12-model_00-model_states.pt... +0: [2022-11-25 18:36:32,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_12-model_00-model_states.pt. +0: [2022-11-25 18:36:32,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_13-model_00-model_states.pt... +0: [2022-11-25 18:36:32,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_13-model_00-model_states.pt. +0: [2022-11-25 18:36:32,191] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_14-model_00-model_states.pt... +0: [2022-11-25 18:36:32,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_14-model_00-model_states.pt. +0: [2022-11-25 18:36:32,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_15-model_00-model_states.pt... +0: [2022-11-25 18:36:32,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_15-model_00-model_states.pt. +0: [2022-11-25 18:36:32,271] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_16-model_00-model_states.pt... +0: [2022-11-25 18:36:32,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_16-model_00-model_states.pt. +0: [2022-11-25 18:36:32,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_17-model_00-model_states.pt... +0: [2022-11-25 18:36:32,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_17-model_00-model_states.pt. +0: [2022-11-25 18:36:32,352] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_18-model_00-model_states.pt... +0: [2022-11-25 18:36:32,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_18-model_00-model_states.pt. +0: [2022-11-25 18:36:32,392] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_19-model_00-model_states.pt... +0: [2022-11-25 18:36:32,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_19-model_00-model_states.pt. +0: [2022-11-25 18:36:32,436] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_20-model_00-model_states.pt... +0: [2022-11-25 18:36:32,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_20-model_00-model_states.pt. +0: [2022-11-25 18:36:32,474] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/layer_22-model_00-model_states.pt... +0: [2022-11-25 18:36:32,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/layer_22-model_00-model_states.pt. +0: [2022-11-25 18:36:32,480] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step5000/mp_rank_00_model_states.pt +0: [2022-11-25 18:36:32,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/mp_rank_00_model_states.pt... +0: [2022-11-25 18:36:32,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/mp_rank_00_model_states.pt. +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:36:32,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:36:32,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-25 18:36:32,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-25 18:36:32,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:36:32,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-25 18:36:32,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +3: [2022-11-25 18:36:32,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:36:32,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +7: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +4: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:36:32,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 18:36:32,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:36:32,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 18:36:32,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +5: [2022-11-25 18:36:32,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 18:36:32,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +1: [2022-11-25 18:36:32,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +6: [2022-11-25 18:36:32,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:36:32,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-25 18:36:32,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:36:32,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +2: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:36:32,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 18:36:32,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: [2022-11-25 18:36:32,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 18:36:32,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +0: successfully saved checkpoint at iteration 5000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1113.43 +7: iteration 5010/ 7508 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.71 | learning rate: 6.568E-05 | global batch size: 256 | lm loss: 2.603100E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 359.560 | TFLOPs: 34.28 | +7: iteration 5020/ 7508 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.59 | learning rate: 6.535E-05 | global batch size: 256 | lm loss: 2.583059E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.308 | TFLOPs: 41.12 | +7: iteration 5030/ 7508 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.59 | learning rate: 6.502E-05 | global batch size: 256 | lm loss: 2.597630E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.289 | TFLOPs: 41.12 | +7: iteration 5040/ 7508 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.57 | learning rate: 6.469E-05 | global batch size: 256 | lm loss: 2.577917E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.021 | TFLOPs: 42.71 | +7: iteration 5050/ 7508 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.59 | learning rate: 6.436E-05 | global batch size: 256 | lm loss: 2.572552E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.615 | TFLOPs: 41.25 | +7: iteration 5060/ 7508 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.58 | learning rate: 6.404E-05 | global batch size: 256 | lm loss: 2.578561E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.013 | TFLOPs: 42.43 | +7: iteration 5070/ 7508 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.58 | learning rate: 6.371E-05 | global batch size: 256 | lm loss: 2.599738E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.749 | TFLOPs: 42.12 | +7: iteration 5080/ 7508 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.58 | learning rate: 6.338E-05 | global batch size: 256 | lm loss: 2.623160E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.897 | TFLOPs: 41.75 | +7: iteration 5090/ 7508 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.57 | learning rate: 6.306E-05 | global batch size: 256 | lm loss: 2.601479E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.106 | TFLOPs: 43.10 | +7: iteration 5100/ 7508 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.59 | learning rate: 6.273E-05 | global batch size: 256 | lm loss: 2.630362E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.370 | TFLOPs: 41.51 | +7: iteration 5110/ 7508 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.56 | learning rate: 6.241E-05 | global batch size: 256 | lm loss: 2.608515E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.327 | TFLOPs: 43.32 | +7: iteration 5120/ 7508 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.57 | learning rate: 6.209E-05 | global batch size: 256 | lm loss: 2.615741E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.475 | TFLOPs: 42.76 | +7: iteration 5130/ 7508 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.59 | learning rate: 6.177E-05 | global batch size: 256 | lm loss: 2.612995E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.735 | TFLOPs: 41.64 | +7: iteration 5140/ 7508 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.57 | learning rate: 6.145E-05 | global batch size: 256 | lm loss: 2.598580E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.332 | TFLOPs: 42.55 | +7: iteration 5150/ 7508 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.58 | learning rate: 6.113E-05 | global batch size: 256 | lm loss: 2.613022E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.866 | TFLOPs: 42.41 | +7: iteration 5160/ 7508 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.57 | learning rate: 6.081E-05 | global batch size: 256 | lm loss: 2.613439E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.313 | TFLOPs: 43.12 | +7: iteration 5170/ 7508 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.58 | learning rate: 6.049E-05 | global batch size: 256 | lm loss: 2.596793E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.149 | TFLOPs: 42.44 | +7: iteration 5180/ 7508 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.58 | learning rate: 6.017E-05 | global batch size: 256 | lm loss: 2.602633E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.665 | TFLOPs: 42.01 | +7: iteration 5190/ 7508 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.58 | learning rate: 5.986E-05 | global batch size: 256 | lm loss: 2.582252E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.756 | TFLOPs: 42.31 | +7: iteration 5200/ 7508 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.57 | learning rate: 5.954E-05 | global batch size: 256 | lm loss: 2.593243E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.230 | TFLOPs: 42.83 | +7: iteration 5210/ 7508 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.58 | learning rate: 5.923E-05 | global batch size: 256 | lm loss: 2.573952E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.867 | TFLOPs: 42.41 | +7: iteration 5220/ 7508 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.58 | learning rate: 5.891E-05 | global batch size: 256 | lm loss: 2.584815E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.251 | TFLOPs: 42.16 | +7: iteration 5230/ 7508 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.57 | learning rate: 5.860E-05 | global batch size: 256 | lm loss: 2.623146E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.700 | TFLOPs: 43.06 | +7: iteration 5240/ 7508 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.57 | learning rate: 5.829E-05 | global batch size: 256 | lm loss: 2.577564E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.240 | TFLOPs: 43.02 | +7: iteration 5250/ 7508 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.57 | learning rate: 5.798E-05 | global batch size: 256 | lm loss: 2.602202E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.726 | TFLOPs: 42.59 | +7: iteration 5260/ 7508 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.59 | learning rate: 5.767E-05 | global batch size: 256 | lm loss: 2.616708E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.843 | TFLOPs: 41.27 | +7: iteration 5270/ 7508 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.59 | learning rate: 5.736E-05 | global batch size: 256 | lm loss: 2.557823E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.850 | TFLOPs: 41.65 | +7: iteration 5280/ 7508 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.59 | learning rate: 5.705E-05 | global batch size: 256 | lm loss: 2.610445E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.973 | TFLOPs: 41.66 | +7: iteration 5290/ 7508 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.58 | learning rate: 5.674E-05 | global batch size: 256 | lm loss: 2.574720E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.951 | TFLOPs: 42.42 | +7: iteration 5300/ 7508 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.58 | learning rate: 5.644E-05 | global batch size: 256 | lm loss: 2.580198E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.182 | TFLOPs: 41.78 | +7: iteration 5310/ 7508 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.56 | learning rate: 5.613E-05 | global batch size: 256 | lm loss: 2.617139E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.763 | TFLOPs: 43.45 | +7: iteration 5320/ 7508 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.58 | learning rate: 5.583E-05 | global batch size: 256 | lm loss: 2.589035E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.229 | TFLOPs: 42.07 | +7: iteration 5330/ 7508 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.60 | learning rate: 5.552E-05 | global batch size: 256 | lm loss: 2.595347E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.760 | TFLOPs: 40.69 | +7: iteration 5340/ 7508 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.57 | learning rate: 5.522E-05 | global batch size: 256 | lm loss: 2.617487E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.638 | TFLOPs: 42.49 | +7: iteration 5350/ 7508 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.57 | learning rate: 5.492E-05 | global batch size: 256 | lm loss: 2.567006E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.770 | TFLOPs: 43.07 | +7: iteration 5360/ 7508 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.56 | learning rate: 5.462E-05 | global batch size: 256 | lm loss: 2.620278E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.146 | TFLOPs: 43.30 | +7: iteration 5370/ 7508 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.57 | learning rate: 5.432E-05 | global batch size: 256 | lm loss: 2.604898E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.096 | TFLOPs: 43.01 | +7: iteration 5380/ 7508 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.58 | learning rate: 5.402E-05 | global batch size: 256 | lm loss: 2.564211E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.329 | TFLOPs: 42.27 | +7: iteration 5390/ 7508 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.58 | learning rate: 5.373E-05 | global batch size: 256 | lm loss: 2.599654E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.474 | TFLOPs: 42.19 | +7: iteration 5400/ 7508 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.61 | learning rate: 5.343E-05 | global batch size: 256 | lm loss: 2.562583E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 420.780 | TFLOPs: 40.12 | +7: iteration 5410/ 7508 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.56 | learning rate: 5.313E-05 | global batch size: 256 | lm loss: 2.597297E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.138 | TFLOPs: 43.30 | +7: iteration 5420/ 7508 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.58 | learning rate: 5.284E-05 | global batch size: 256 | lm loss: 2.584464E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.309 | TFLOPs: 41.79 | +7: iteration 5430/ 7508 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.58 | learning rate: 5.255E-05 | global batch size: 256 | lm loss: 2.607980E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.567 | TFLOPs: 42.19 | +7: iteration 5440/ 7508 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.59 | learning rate: 5.225E-05 | global batch size: 256 | lm loss: 2.590766E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.611 | TFLOPs: 41.15 | +7: iteration 5450/ 7508 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.58 | learning rate: 5.196E-05 | global batch size: 256 | lm loss: 2.595638E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.755 | TFLOPs: 42.40 | +7: iteration 5460/ 7508 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.58 | learning rate: 5.167E-05 | global batch size: 256 | lm loss: 2.614403E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.592 | TFLOPs: 41.91 | +7: iteration 5470/ 7508 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.59 | learning rate: 5.138E-05 | global batch size: 256 | lm loss: 2.591217E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.363 | TFLOPs: 41.13 | +7: iteration 5480/ 7508 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.59 | learning rate: 5.109E-05 | global batch size: 256 | lm loss: 2.588427E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.941 | TFLOPs: 41.66 | +7: iteration 5490/ 7508 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.60 | learning rate: 5.081E-05 | global batch size: 256 | lm loss: 2.561609E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.990 | TFLOPs: 40.71 | +7: iteration 5500/ 7508 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.58 | learning rate: 5.052E-05 | global batch size: 256 | lm loss: 2.621561E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.508 | TFLOPs: 42.28 | +7: iteration 5510/ 7508 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.58 | learning rate: 5.024E-05 | global batch size: 256 | lm loss: 2.587766E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.183 | TFLOPs: 42.35 | +7: iteration 5520/ 7508 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.59 | learning rate: 4.995E-05 | global batch size: 256 | lm loss: 2.618786E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.256 | TFLOPs: 41.50 | +7: iteration 5530/ 7508 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.58 | learning rate: 4.967E-05 | global batch size: 256 | lm loss: 2.586938E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.188 | TFLOPs: 42.25 | +7: iteration 5540/ 7508 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.58 | learning rate: 4.939E-05 | global batch size: 256 | lm loss: 2.627142E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.121 | TFLOPs: 41.77 | +7: iteration 5550/ 7508 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.59 | learning rate: 4.911E-05 | global batch size: 256 | lm loss: 2.593897E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.877 | TFLOPs: 41.46 | +7: iteration 5560/ 7508 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.58 | learning rate: 4.883E-05 | global batch size: 256 | lm loss: 2.584924E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.936 | TFLOPs: 42.42 | +7: iteration 5570/ 7508 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.59 | learning rate: 4.855E-05 | global batch size: 256 | lm loss: 2.609874E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.005 | TFLOPs: 41.19 | +7: iteration 5580/ 7508 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.59 | learning rate: 4.827E-05 | global batch size: 256 | lm loss: 2.572293E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.109 | TFLOPs: 41.10 | +7: iteration 5590/ 7508 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.57 | learning rate: 4.800E-05 | global batch size: 256 | lm loss: 2.582913E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.960 | TFLOPs: 42.61 | +7: iteration 5600/ 7508 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.58 | learning rate: 4.772E-05 | global batch size: 256 | lm loss: 2.569448E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.449 | TFLOPs: 42.18 | +7: iteration 5610/ 7508 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.61 | learning rate: 4.745E-05 | global batch size: 256 | lm loss: 2.623744E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.198 | TFLOPs: 40.25 | +7: iteration 5620/ 7508 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.57 | learning rate: 4.717E-05 | global batch size: 256 | lm loss: 2.572579E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.689 | TFLOPs: 43.16 | +7: iteration 5630/ 7508 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.57 | learning rate: 4.690E-05 | global batch size: 256 | lm loss: 2.621907E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.343 | TFLOPs: 43.03 | +7: iteration 5640/ 7508 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.58 | learning rate: 4.663E-05 | global batch size: 256 | lm loss: 2.542610E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.989 | TFLOPs: 42.04 | +7: iteration 5650/ 7508 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.60 | learning rate: 4.636E-05 | global batch size: 256 | lm loss: 2.592087E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.714 | TFLOPs: 40.97 | +7: iteration 5660/ 7508 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.59 | learning rate: 4.609E-05 | global batch size: 256 | lm loss: 2.575092E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.776 | TFLOPs: 41.36 | +7: iteration 5670/ 7508 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.59 | learning rate: 4.583E-05 | global batch size: 256 | lm loss: 2.610796E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.009 | TFLOPs: 41.28 | +7: iteration 5680/ 7508 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.57 | learning rate: 4.556E-05 | global batch size: 256 | lm loss: 2.593444E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.630 | TFLOPs: 42.49 | +7: iteration 5690/ 7508 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.58 | learning rate: 4.530E-05 | global batch size: 256 | lm loss: 2.634382E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.927 | TFLOPs: 41.85 | +7: iteration 5700/ 7508 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.57 | learning rate: 4.503E-05 | global batch size: 256 | lm loss: 2.609970E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.475 | TFLOPs: 43.14 | +7: iteration 5710/ 7508 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.58 | learning rate: 4.477E-05 | global batch size: 256 | lm loss: 2.580767E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.881 | TFLOPs: 42.32 | +7: iteration 5720/ 7508 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.57 | learning rate: 4.451E-05 | global batch size: 256 | lm loss: 2.562688E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.479 | TFLOPs: 42.57 | +7: iteration 5730/ 7508 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.57 | learning rate: 4.425E-05 | global batch size: 256 | lm loss: 2.608625E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.370 | TFLOPs: 42.84 | +7: iteration 5740/ 7508 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.57 | learning rate: 4.399E-05 | global batch size: 256 | lm loss: 2.580037E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.220 | TFLOPs: 42.45 | +7: iteration 5750/ 7508 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.61 | learning rate: 4.373E-05 | global batch size: 256 | lm loss: 2.540541E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 422.865 | TFLOPs: 40.32 | +7: iteration 5760/ 7508 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.57 | learning rate: 4.347E-05 | global batch size: 256 | lm loss: 2.578088E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.820 | TFLOPs: 42.60 | +7: iteration 5770/ 7508 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.57 | learning rate: 4.322E-05 | global batch size: 256 | lm loss: 2.570514E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.095 | TFLOPs: 42.63 | +7: iteration 5780/ 7508 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.59 | learning rate: 4.296E-05 | global batch size: 256 | lm loss: 2.571688E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.710 | TFLOPs: 41.25 | +7: iteration 5790/ 7508 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.59 | learning rate: 4.271E-05 | global batch size: 256 | lm loss: 2.583677E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.814 | TFLOPs: 41.55 | +7: iteration 5800/ 7508 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.58 | learning rate: 4.246E-05 | global batch size: 256 | lm loss: 2.603377E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.521 | TFLOPs: 42.00 | +7: iteration 5810/ 7508 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.58 | learning rate: 4.221E-05 | global batch size: 256 | lm loss: 2.569792E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.746 | TFLOPs: 41.73 | +7: iteration 5820/ 7508 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.59 | learning rate: 4.196E-05 | global batch size: 256 | lm loss: 2.601306E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.505 | TFLOPs: 41.62 | +7: iteration 5830/ 7508 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.59 | learning rate: 4.171E-05 | global batch size: 256 | lm loss: 2.568189E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.308 | TFLOPs: 41.69 | +7: iteration 5840/ 7508 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.57 | learning rate: 4.146E-05 | global batch size: 256 | lm loss: 2.585736E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.197 | TFLOPs: 42.92 | +7: iteration 5850/ 7508 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.58 | learning rate: 4.122E-05 | global batch size: 256 | lm loss: 2.592749E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.631 | TFLOPs: 42.30 | +7: iteration 5860/ 7508 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.60 | learning rate: 4.097E-05 | global batch size: 256 | lm loss: 2.584148E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.831 | TFLOPs: 40.98 | +7: iteration 5870/ 7508 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.60 | learning rate: 4.073E-05 | global batch size: 256 | lm loss: 2.585382E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.933 | TFLOPs: 40.80 | +7: iteration 5880/ 7508 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.56 | learning rate: 4.049E-05 | global batch size: 256 | lm loss: 2.581865E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.246 | TFLOPs: 43.21 | +7: iteration 5890/ 7508 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.58 | learning rate: 4.025E-05 | global batch size: 256 | lm loss: 2.543227E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.337 | TFLOPs: 42.36 | +7: iteration 5900/ 7508 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.57 | learning rate: 4.001E-05 | global batch size: 256 | lm loss: 2.555412E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.574 | TFLOPs: 42.58 | +7: iteration 5910/ 7508 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.59 | learning rate: 3.977E-05 | global batch size: 256 | lm loss: 2.574742E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.386 | TFLOPs: 41.22 | +7: iteration 5920/ 7508 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.59 | learning rate: 3.953E-05 | global batch size: 256 | lm loss: 2.595177E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.116 | TFLOPs: 41.48 | +7: iteration 5930/ 7508 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.56 | learning rate: 3.929E-05 | global batch size: 256 | lm loss: 2.572886E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 453.885 | TFLOPs: 43.27 | +7: iteration 5940/ 7508 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.59 | learning rate: 3.906E-05 | global batch size: 256 | lm loss: 2.578132E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.828 | TFLOPs: 41.46 | +7: iteration 5950/ 7508 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.57 | learning rate: 3.883E-05 | global batch size: 256 | lm loss: 2.586790E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.860 | TFLOPs: 42.79 | +7: iteration 5960/ 7508 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.57 | learning rate: 3.859E-05 | global batch size: 256 | lm loss: 2.583191E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.747 | TFLOPs: 42.78 | +7: iteration 5970/ 7508 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.59 | learning rate: 3.836E-05 | global batch size: 256 | lm loss: 2.621898E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.842 | TFLOPs: 41.17 | +7: iteration 5980/ 7508 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.58 | learning rate: 3.813E-05 | global batch size: 256 | lm loss: 2.582457E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.952 | TFLOPs: 41.75 | +7: iteration 5990/ 7508 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.57 | learning rate: 3.790E-05 | global batch size: 256 | lm loss: 2.589144E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.659 | TFLOPs: 42.68 | +0: [2022-11-25 18:46:12,807] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[3.76774148080129e-05, 3.76774148080129e-05, 3.76774148080129e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +7: iteration 6000/ 7508 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.56 | learning rate: 3.768E-05 | global batch size: 256 | lm loss: 2.578170E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.956 | TFLOPs: 43.47 | +0: steps: 6000 loss: 2.5864 iter time (s): 0.577 samples/sec: 443.762 +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 6000 | lm loss value: 2.598804E+00 | lm loss PPL: 1.344764E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 6000 to checkpoints_421m +0: [2022-11-25 18:46:13,011] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! +0: [2022-11-25 18:46:13,015] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_01-model_00-model_states.pt... +0: [2022-11-25 18:46:13,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_01-model_00-model_states.pt. +0: [2022-11-25 18:46:13,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_03-model_00-model_states.pt... +0: [2022-11-25 18:46:13,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_03-model_00-model_states.pt. +0: [2022-11-25 18:46:13,198] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_04-model_00-model_states.pt... +0: [2022-11-25 18:46:13,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_04-model_00-model_states.pt. +0: [2022-11-25 18:46:13,239] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_05-model_00-model_states.pt... +0: [2022-11-25 18:46:13,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_05-model_00-model_states.pt. +0: [2022-11-25 18:46:13,281] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_06-model_00-model_states.pt... +0: [2022-11-25 18:46:13,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_06-model_00-model_states.pt. +0: [2022-11-25 18:46:13,321] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_07-model_00-model_states.pt... +0: [2022-11-25 18:46:13,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_07-model_00-model_states.pt. +0: [2022-11-25 18:46:13,363] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_08-model_00-model_states.pt... +0: [2022-11-25 18:46:13,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_08-model_00-model_states.pt. +0: [2022-11-25 18:46:13,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_09-model_00-model_states.pt... +0: [2022-11-25 18:46:13,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_09-model_00-model_states.pt. +0: [2022-11-25 18:46:13,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_10-model_00-model_states.pt... +0: [2022-11-25 18:46:13,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_10-model_00-model_states.pt. +0: [2022-11-25 18:46:13,481] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_11-model_00-model_states.pt... +0: [2022-11-25 18:46:13,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_11-model_00-model_states.pt. +0: [2022-11-25 18:46:13,525] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_12-model_00-model_states.pt... +0: [2022-11-25 18:46:13,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_12-model_00-model_states.pt. +0: [2022-11-25 18:46:13,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_13-model_00-model_states.pt... +0: [2022-11-25 18:46:13,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_13-model_00-model_states.pt. +0: [2022-11-25 18:46:13,606] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_14-model_00-model_states.pt... +0: [2022-11-25 18:46:13,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_14-model_00-model_states.pt. +0: [2022-11-25 18:46:13,646] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_15-model_00-model_states.pt... +0: [2022-11-25 18:46:13,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_15-model_00-model_states.pt. +0: [2022-11-25 18:46:13,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_16-model_00-model_states.pt... +0: [2022-11-25 18:46:13,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_16-model_00-model_states.pt. +0: [2022-11-25 18:46:13,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_17-model_00-model_states.pt... +0: [2022-11-25 18:46:13,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_17-model_00-model_states.pt. +0: [2022-11-25 18:46:13,772] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_18-model_00-model_states.pt... +0: [2022-11-25 18:46:13,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_18-model_00-model_states.pt. +0: [2022-11-25 18:46:13,810] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_19-model_00-model_states.pt... +0: [2022-11-25 18:46:13,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_19-model_00-model_states.pt. +0: [2022-11-25 18:46:13,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_20-model_00-model_states.pt... +0: [2022-11-25 18:46:13,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_20-model_00-model_states.pt. +0: [2022-11-25 18:46:13,890] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/layer_22-model_00-model_states.pt... +0: [2022-11-25 18:46:13,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/layer_22-model_00-model_states.pt. +0: [2022-11-25 18:46:13,895] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step6000/mp_rank_00_model_states.pt +0: [2022-11-25 18:46:13,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/mp_rank_00_model_states.pt... +0: [2022-11-25 18:46:13,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/mp_rank_00_model_states.pt. +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:46:13,915] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:46:14,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:46:14,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-25 18:46:14,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +5: [2022-11-25 18:46:14,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +6: [2022-11-25 18:46:14,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:46:14,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-25 18:46:14,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +7: [2022-11-25 18:46:14,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,022] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,022] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,022] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,022] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +3: [2022-11-25 18:46:14,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:46:14,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 18:46:14,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:46:14,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:46:14,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:46:14,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:46:14,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 18:46:14,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +4: [2022-11-25 18:46:14,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:46:14,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 18:46:14,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:46:14,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:46:14,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +1: [2022-11-25 18:46:14,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:46:14,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 18:46:14,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +2: [2022-11-25 18:46:14,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:46:14,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 18:46:14,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: [2022-11-25 18:46:14,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 18:46:14,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +0: successfully saved checkpoint at iteration 6000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1123.67 +7: iteration 6010/ 7508 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.72 | learning rate: 3.745E-05 | global batch size: 256 | lm loss: 2.603970E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 357.067 | TFLOPs: 34.04 | +7: iteration 6020/ 7508 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.57 | learning rate: 3.723E-05 | global batch size: 256 | lm loss: 2.568882E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.353 | TFLOPs: 42.65 | +7: iteration 6030/ 7508 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.60 | learning rate: 3.700E-05 | global batch size: 256 | lm loss: 2.563192E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 429.639 | TFLOPs: 40.96 | +7: iteration 6040/ 7508 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.57 | learning rate: 3.678E-05 | global batch size: 256 | lm loss: 2.607557E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.617 | TFLOPs: 42.87 | +7: iteration 6050/ 7508 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.58 | learning rate: 3.656E-05 | global batch size: 256 | lm loss: 2.552013E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.501 | TFLOPs: 42.19 | +7: iteration 6060/ 7508 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.58 | learning rate: 3.634E-05 | global batch size: 256 | lm loss: 2.563131E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.901 | TFLOPs: 41.75 | +7: iteration 6070/ 7508 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.58 | learning rate: 3.612E-05 | global batch size: 256 | lm loss: 2.598378E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.767 | TFLOPs: 42.02 | +7: iteration 6080/ 7508 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.56 | learning rate: 3.591E-05 | global batch size: 256 | lm loss: 2.589242E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.476 | TFLOPs: 43.42 | +7: iteration 6090/ 7508 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.57 | learning rate: 3.569E-05 | global batch size: 256 | lm loss: 2.567285E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.687 | TFLOPs: 42.97 | +7: iteration 6100/ 7508 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.58 | learning rate: 3.548E-05 | global batch size: 256 | lm loss: 2.590623E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.466 | TFLOPs: 41.99 | +7: iteration 6110/ 7508 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.57 | learning rate: 3.527E-05 | global batch size: 256 | lm loss: 2.559102E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.576 | TFLOPs: 43.15 | +7: iteration 6120/ 7508 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.58 | learning rate: 3.505E-05 | global batch size: 256 | lm loss: 2.541364E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.759 | TFLOPs: 41.74 | +7: iteration 6130/ 7508 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.59 | learning rate: 3.484E-05 | global batch size: 256 | lm loss: 2.576647E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 433.625 | TFLOPs: 41.34 | +7: iteration 6140/ 7508 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.60 | learning rate: 3.464E-05 | global batch size: 256 | lm loss: 2.561650E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 427.559 | TFLOPs: 40.76 | +7: iteration 6150/ 7508 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.57 | learning rate: 3.443E-05 | global batch size: 256 | lm loss: 2.564732E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.200 | TFLOPs: 43.02 | +7: iteration 6160/ 7508 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.57 | learning rate: 3.422E-05 | global batch size: 256 | lm loss: 2.555347E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.458 | TFLOPs: 42.66 | +7: iteration 6170/ 7508 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.59 | learning rate: 3.402E-05 | global batch size: 256 | lm loss: 2.563937E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.217 | TFLOPs: 41.68 | +7: iteration 6180/ 7508 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.59 | learning rate: 3.382E-05 | global batch size: 256 | lm loss: 2.551921E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.247 | TFLOPs: 41.40 | +7: iteration 6190/ 7508 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.57 | learning rate: 3.361E-05 | global batch size: 256 | lm loss: 2.585773E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.853 | TFLOPs: 43.08 | +7: iteration 6200/ 7508 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.59 | learning rate: 3.341E-05 | global batch size: 256 | lm loss: 2.572375E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.992 | TFLOPs: 41.57 | +7: iteration 6210/ 7508 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.57 | learning rate: 3.321E-05 | global batch size: 256 | lm loss: 2.606342E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.573 | TFLOPs: 42.96 | +7: iteration 6220/ 7508 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.57 | learning rate: 3.302E-05 | global batch size: 256 | lm loss: 2.581815E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.365 | TFLOPs: 42.65 | +7: iteration 6230/ 7508 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.57 | learning rate: 3.282E-05 | global batch size: 256 | lm loss: 2.598807E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.866 | TFLOPs: 43.18 | +7: iteration 6240/ 7508 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.57 | learning rate: 3.262E-05 | global batch size: 256 | lm loss: 2.595494E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.311 | TFLOPs: 42.46 | +7: iteration 6250/ 7508 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.57 | learning rate: 3.243E-05 | global batch size: 256 | lm loss: 2.554085E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.954 | TFLOPs: 42.80 | +7: iteration 6260/ 7508 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.57 | learning rate: 3.224E-05 | global batch size: 256 | lm loss: 2.591592E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.995 | TFLOPs: 42.81 | +7: iteration 6270/ 7508 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.58 | learning rate: 3.205E-05 | global batch size: 256 | lm loss: 2.562273E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.085 | TFLOPs: 42.15 | +7: iteration 6280/ 7508 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.57 | learning rate: 3.186E-05 | global batch size: 256 | lm loss: 2.557878E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.662 | TFLOPs: 42.58 | +7: iteration 6290/ 7508 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.60 | learning rate: 3.167E-05 | global batch size: 256 | lm loss: 2.552389E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.472 | TFLOPs: 40.85 | +7: iteration 6300/ 7508 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.58 | learning rate: 3.148E-05 | global batch size: 256 | lm loss: 2.561096E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.793 | TFLOPs: 42.41 | +7: iteration 6310/ 7508 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.58 | learning rate: 3.130E-05 | global batch size: 256 | lm loss: 2.547566E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.207 | TFLOPs: 42.45 | +7: iteration 6320/ 7508 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.57 | learning rate: 3.112E-05 | global batch size: 256 | lm loss: 2.570915E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.666 | TFLOPs: 42.49 | +7: iteration 6330/ 7508 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.58 | learning rate: 3.093E-05 | global batch size: 256 | lm loss: 2.600083E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.756 | TFLOPs: 42.31 | +7: iteration 6340/ 7508 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.59 | learning rate: 3.075E-05 | global batch size: 256 | lm loss: 2.529529E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.412 | TFLOPs: 41.13 | +7: iteration 6350/ 7508 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.58 | learning rate: 3.057E-05 | global batch size: 256 | lm loss: 2.567704E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.921 | TFLOPs: 42.13 | +7: iteration 6360/ 7508 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.58 | learning rate: 3.039E-05 | global batch size: 256 | lm loss: 2.561595E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.917 | TFLOPs: 41.75 | +7: iteration 6370/ 7508 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.59 | learning rate: 3.022E-05 | global batch size: 256 | lm loss: 2.583899E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 437.329 | TFLOPs: 41.69 | +7: iteration 6380/ 7508 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.58 | learning rate: 3.004E-05 | global batch size: 256 | lm loss: 2.549112E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.050 | TFLOPs: 42.34 | +7: iteration 6390/ 7508 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.57 | learning rate: 2.987E-05 | global batch size: 256 | lm loss: 2.560099E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.668 | TFLOPs: 42.58 | +7: iteration 6400/ 7508 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.57 | learning rate: 2.970E-05 | global batch size: 256 | lm loss: 2.559963E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.429 | TFLOPs: 42.47 | +7: iteration 6410/ 7508 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.59 | learning rate: 2.952E-05 | global batch size: 256 | lm loss: 2.583660E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.883 | TFLOPs: 41.08 | +7: iteration 6420/ 7508 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.57 | learning rate: 2.936E-05 | global batch size: 256 | lm loss: 2.540050E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.623 | TFLOPs: 42.87 | +7: iteration 6430/ 7508 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.59 | learning rate: 2.919E-05 | global batch size: 256 | lm loss: 2.561089E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.618 | TFLOPs: 41.53 | +7: iteration 6440/ 7508 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.60 | learning rate: 2.902E-05 | global batch size: 256 | lm loss: 2.566621E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 425.070 | TFLOPs: 40.53 | +7: iteration 6450/ 7508 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.61 | learning rate: 2.886E-05 | global batch size: 256 | lm loss: 2.559661E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 419.654 | TFLOPs: 40.01 | +7: iteration 6460/ 7508 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.59 | learning rate: 2.869E-05 | global batch size: 256 | lm loss: 2.525071E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.380 | TFLOPs: 41.13 | +7: iteration 6470/ 7508 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.57 | learning rate: 2.853E-05 | global batch size: 256 | lm loss: 2.542830E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.443 | TFLOPs: 43.14 | +7: iteration 6480/ 7508 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.59 | learning rate: 2.837E-05 | global batch size: 256 | lm loss: 2.571726E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 430.256 | TFLOPs: 41.02 | +7: iteration 6490/ 7508 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.59 | learning rate: 2.821E-05 | global batch size: 256 | lm loss: 2.553388E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.022 | TFLOPs: 41.57 | +7: iteration 6500/ 7508 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.58 | learning rate: 2.805E-05 | global batch size: 256 | lm loss: 2.531295E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.941 | TFLOPs: 42.32 | +7: iteration 6510/ 7508 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.57 | learning rate: 2.789E-05 | global batch size: 256 | lm loss: 2.562675E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.604 | TFLOPs: 42.77 | +7: iteration 6520/ 7508 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.57 | learning rate: 2.774E-05 | global batch size: 256 | lm loss: 2.575592E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.300 | TFLOPs: 42.84 | +7: iteration 6530/ 7508 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.58 | learning rate: 2.759E-05 | global batch size: 256 | lm loss: 2.539861E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.094 | TFLOPs: 42.43 | +7: iteration 6540/ 7508 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.58 | learning rate: 2.743E-05 | global batch size: 256 | lm loss: 2.545416E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.087 | TFLOPs: 42.15 | +7: iteration 6550/ 7508 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.57 | learning rate: 2.728E-05 | global batch size: 256 | lm loss: 2.576631E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.849 | TFLOPs: 42.51 | +7: iteration 6560/ 7508 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.56 | learning rate: 2.713E-05 | global batch size: 256 | lm loss: 2.561005E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.470 | TFLOPs: 43.33 | +7: iteration 6570/ 7508 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.58 | learning rate: 2.699E-05 | global batch size: 256 | lm loss: 2.561303E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.543 | TFLOPs: 42.38 | +7: iteration 6580/ 7508 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.65 | learning rate: 2.684E-05 | global batch size: 256 | lm loss: 2.570686E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 394.787 | TFLOPs: 37.64 | +7: iteration 6590/ 7508 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.61 | learning rate: 2.669E-05 | global batch size: 256 | lm loss: 2.557512E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 417.955 | TFLOPs: 39.85 | +7: iteration 6600/ 7508 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.64 | learning rate: 2.655E-05 | global batch size: 256 | lm loss: 2.558402E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 403.014 | TFLOPs: 38.42 | +7: iteration 6610/ 7508 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.68 | learning rate: 2.641E-05 | global batch size: 256 | lm loss: 2.562851E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 378.829 | TFLOPs: 36.12 | +7: iteration 6620/ 7508 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.57 | learning rate: 2.627E-05 | global batch size: 256 | lm loss: 2.536079E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.338 | TFLOPs: 42.46 | +7: iteration 6630/ 7508 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.57 | learning rate: 2.613E-05 | global batch size: 256 | lm loss: 2.566274E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.284 | TFLOPs: 42.74 | +7: iteration 6640/ 7508 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.57 | learning rate: 2.599E-05 | global batch size: 256 | lm loss: 2.538453E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.903 | TFLOPs: 43.18 | +7: iteration 6650/ 7508 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.58 | learning rate: 2.586E-05 | global batch size: 256 | lm loss: 2.525006E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.374 | TFLOPs: 41.98 | +7: iteration 6660/ 7508 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.58 | learning rate: 2.572E-05 | global batch size: 256 | lm loss: 2.579054E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.042 | TFLOPs: 41.76 | +7: iteration 6670/ 7508 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.59 | learning rate: 2.559E-05 | global batch size: 256 | lm loss: 2.543869E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.255 | TFLOPs: 41.59 | +7: iteration 6680/ 7508 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.57 | learning rate: 2.546E-05 | global batch size: 256 | lm loss: 2.536828E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.253 | TFLOPs: 42.55 | +7: iteration 6690/ 7508 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.56 | learning rate: 2.533E-05 | global batch size: 256 | lm loss: 2.555995E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.578 | TFLOPs: 43.34 | +7: iteration 6700/ 7508 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.57 | learning rate: 2.520E-05 | global batch size: 256 | lm loss: 2.562953E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.202 | TFLOPs: 42.83 | +7: iteration 6710/ 7508 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.58 | learning rate: 2.508E-05 | global batch size: 256 | lm loss: 2.577835E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.203 | TFLOPs: 41.87 | +7: iteration 6720/ 7508 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.57 | learning rate: 2.495E-05 | global batch size: 256 | lm loss: 2.534459E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.509 | TFLOPs: 42.67 | +7: iteration 6730/ 7508 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.56 | learning rate: 2.483E-05 | global batch size: 256 | lm loss: 2.580565E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 456.991 | TFLOPs: 43.57 | +7: iteration 6740/ 7508 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.58 | learning rate: 2.470E-05 | global batch size: 256 | lm loss: 2.555781E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.805 | TFLOPs: 41.84 | +7: iteration 6750/ 7508 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.57 | learning rate: 2.458E-05 | global batch size: 256 | lm loss: 2.532838E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.489 | TFLOPs: 42.76 | +7: iteration 6760/ 7508 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.58 | learning rate: 2.446E-05 | global batch size: 256 | lm loss: 2.553916E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.347 | TFLOPs: 42.17 | +7: iteration 6770/ 7508 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.57 | learning rate: 2.435E-05 | global batch size: 256 | lm loss: 2.515966E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.713 | TFLOPs: 42.78 | +7: iteration 6780/ 7508 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.59 | learning rate: 2.423E-05 | global batch size: 256 | lm loss: 2.528861E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 432.847 | TFLOPs: 41.27 | +7: iteration 6790/ 7508 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.59 | learning rate: 2.412E-05 | global batch size: 256 | lm loss: 2.552453E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.268 | TFLOPs: 41.12 | +7: iteration 6800/ 7508 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.57 | learning rate: 2.400E-05 | global batch size: 256 | lm loss: 2.601506E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.108 | TFLOPs: 42.63 | +7: iteration 6810/ 7508 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.58 | learning rate: 2.389E-05 | global batch size: 256 | lm loss: 2.544288E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.646 | TFLOPs: 42.30 | +7: iteration 6820/ 7508 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.59 | learning rate: 2.378E-05 | global batch size: 256 | lm loss: 2.546181E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 436.556 | TFLOPs: 41.62 | +7: iteration 6830/ 7508 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.60 | learning rate: 2.367E-05 | global batch size: 256 | lm loss: 2.562177E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 426.649 | TFLOPs: 40.68 | +7: iteration 6840/ 7508 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.58 | learning rate: 2.357E-05 | global batch size: 256 | lm loss: 2.553573E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.978 | TFLOPs: 42.23 | +7: iteration 6850/ 7508 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.57 | learning rate: 2.346E-05 | global batch size: 256 | lm loss: 2.549096E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.047 | TFLOPs: 42.53 | +7: iteration 6860/ 7508 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.58 | learning rate: 2.336E-05 | global batch size: 256 | lm loss: 2.531415E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.097 | TFLOPs: 42.24 | +7: iteration 6870/ 7508 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.57 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 2.583199E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.268 | TFLOPs: 42.83 | +7: iteration 6880/ 7508 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.58 | learning rate: 2.316E-05 | global batch size: 256 | lm loss: 2.569813E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.068 | TFLOPs: 41.86 | +7: iteration 6890/ 7508 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.58 | learning rate: 2.306E-05 | global batch size: 256 | lm loss: 2.504131E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.033 | TFLOPs: 42.33 | +7: iteration 6900/ 7508 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.57 | learning rate: 2.296E-05 | global batch size: 256 | lm loss: 2.511622E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.221 | TFLOPs: 42.92 | +7: iteration 6910/ 7508 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.58 | learning rate: 2.286E-05 | global batch size: 256 | lm loss: 2.548623E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.323 | TFLOPs: 42.27 | +7: iteration 6920/ 7508 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.59 | learning rate: 2.277E-05 | global batch size: 256 | lm loss: 2.545210E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.188 | TFLOPs: 41.40 | +7: iteration 6930/ 7508 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.58 | learning rate: 2.268E-05 | global batch size: 256 | lm loss: 2.540047E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.942 | TFLOPs: 42.04 | +7: iteration 6940/ 7508 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.57 | learning rate: 2.258E-05 | global batch size: 256 | lm loss: 2.560343E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.672 | TFLOPs: 43.16 | +7: iteration 6950/ 7508 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.56 | learning rate: 2.249E-05 | global batch size: 256 | lm loss: 2.535736E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 458.426 | TFLOPs: 43.71 | +7: iteration 6960/ 7508 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.60 | learning rate: 2.241E-05 | global batch size: 256 | lm loss: 2.579086E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.028 | TFLOPs: 40.81 | +7: iteration 6970/ 7508 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.58 | learning rate: 2.232E-05 | global batch size: 256 | lm loss: 2.535657E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.440 | TFLOPs: 42.37 | +7: iteration 6980/ 7508 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.57 | learning rate: 2.223E-05 | global batch size: 256 | lm loss: 2.516400E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.134 | TFLOPs: 42.53 | +7: iteration 6990/ 7508 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.58 | learning rate: 2.215E-05 | global batch size: 256 | lm loss: 2.571073E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.938 | TFLOPs: 41.85 | +7: iteration 7000/ 7508 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.57 | learning rate: 2.207E-05 | global batch size: 256 | lm loss: 2.557619E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.413 | TFLOPs: 42.56 | +7: ------------------------------------------------------------------------------------------ +7: valid loss at iteration 7000 | lm loss value: 2.509978E+00 | lm loss PPL: 1.230466E+01 | +7: ------------------------------------------------------------------------------------------ +0: saving checkpoint at iteration 7000 to checkpoints_421m +0: [2022-11-25 18:55:55,354] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! +0: [2022-11-25 18:55:55,360] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_01-model_00-model_states.pt... +0: [2022-11-25 18:55:55,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_01-model_00-model_states.pt. +0: [2022-11-25 18:55:55,577] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_03-model_00-model_states.pt... +0: [2022-11-25 18:55:55,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_03-model_00-model_states.pt. +0: [2022-11-25 18:55:55,622] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_04-model_00-model_states.pt... +0: [2022-11-25 18:55:55,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_04-model_00-model_states.pt. +0: [2022-11-25 18:55:55,666] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_05-model_00-model_states.pt... +0: [2022-11-25 18:55:55,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_05-model_00-model_states.pt. +0: [2022-11-25 18:55:55,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_06-model_00-model_states.pt... +0: [2022-11-25 18:55:55,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_06-model_00-model_states.pt. +0: [2022-11-25 18:55:55,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_07-model_00-model_states.pt... +0: [2022-11-25 18:55:55,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_07-model_00-model_states.pt. +0: [2022-11-25 18:55:55,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_08-model_00-model_states.pt... +0: [2022-11-25 18:55:55,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_08-model_00-model_states.pt. +0: [2022-11-25 18:55:55,841] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_09-model_00-model_states.pt... +0: [2022-11-25 18:55:55,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_09-model_00-model_states.pt. +0: [2022-11-25 18:55:55,884] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_10-model_00-model_states.pt... +0: [2022-11-25 18:55:55,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_10-model_00-model_states.pt. +0: [2022-11-25 18:55:55,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_11-model_00-model_states.pt... +0: [2022-11-25 18:55:55,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_11-model_00-model_states.pt. +0: [2022-11-25 18:55:55,973] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_12-model_00-model_states.pt... +0: [2022-11-25 18:55:56,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_12-model_00-model_states.pt. +0: [2022-11-25 18:55:56,017] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_13-model_00-model_states.pt... +0: [2022-11-25 18:55:56,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_13-model_00-model_states.pt. +0: [2022-11-25 18:55:56,060] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_14-model_00-model_states.pt... +0: [2022-11-25 18:55:56,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_14-model_00-model_states.pt. +0: [2022-11-25 18:55:56,104] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_15-model_00-model_states.pt... +0: [2022-11-25 18:55:56,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_15-model_00-model_states.pt. +0: [2022-11-25 18:55:56,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_16-model_00-model_states.pt... +0: [2022-11-25 18:55:56,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_16-model_00-model_states.pt. +0: [2022-11-25 18:55:56,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_17-model_00-model_states.pt... +0: [2022-11-25 18:55:56,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_17-model_00-model_states.pt. +0: [2022-11-25 18:55:56,237] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_18-model_00-model_states.pt... +0: [2022-11-25 18:55:56,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_18-model_00-model_states.pt. +0: [2022-11-25 18:55:56,280] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_19-model_00-model_states.pt... +0: [2022-11-25 18:55:56,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_19-model_00-model_states.pt. +0: [2022-11-25 18:55:56,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_20-model_00-model_states.pt... +0: [2022-11-25 18:55:56,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_20-model_00-model_states.pt. +0: [2022-11-25 18:55:56,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/layer_22-model_00-model_states.pt... +0: [2022-11-25 18:55:56,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/layer_22-model_00-model_states.pt. +0: [2022-11-25 18:55:56,373] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step7000/mp_rank_00_model_states.pt +0: [2022-11-25 18:55:56,373] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/mp_rank_00_model_states.pt... +0: [2022-11-25 18:55:56,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/mp_rank_00_model_states.pt. +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +0: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +2: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +3: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-25 18:55:56,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +1: [2022-11-25 18:55:56,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 18:55:56,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-25 18:55:56,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +6: [2022-11-25 18:55:56,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +1: [2022-11-25 18:55:56,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 18:55:56,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 18:55:56,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +5: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 18:55:56,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +3: [2022-11-25 18:55:56,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +4: [2022-11-25 18:55:56,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: [2022-11-25 18:55:56,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 18:55:56,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +7: [2022-11-25 18:55:56,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +2: [2022-11-25 18:55:56,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 18:55:56,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 18:55:56,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +0: successfully saved checkpoint at iteration 7000 to checkpoints_421m +7: time (ms) | save-checkpoint: 1322.69 +7: iteration 7010/ 7508 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.72 | learning rate: 2.199E-05 | global batch size: 256 | lm loss: 2.532302E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 354.818 | TFLOPs: 33.83 | +7: iteration 7020/ 7508 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.57 | learning rate: 2.191E-05 | global batch size: 256 | lm loss: 2.583894E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.112 | TFLOPs: 42.82 | +7: iteration 7030/ 7508 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.58 | learning rate: 2.183E-05 | global batch size: 256 | lm loss: 2.523949E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 438.546 | TFLOPs: 41.81 | +7: iteration 7040/ 7508 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.57 | learning rate: 2.176E-05 | global batch size: 256 | lm loss: 2.562704E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.325 | TFLOPs: 42.84 | +7: iteration 7050/ 7508 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.57 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.563953E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.370 | TFLOPs: 42.56 | +7: iteration 7060/ 7508 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.57 | learning rate: 2.161E-05 | global batch size: 256 | lm loss: 2.534064E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.605 | TFLOPs: 42.48 | +7: iteration 7070/ 7508 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.57 | learning rate: 2.154E-05 | global batch size: 256 | lm loss: 2.552073E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 449.662 | TFLOPs: 42.87 | +7: iteration 7080/ 7508 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.57 | learning rate: 2.147E-05 | global batch size: 256 | lm loss: 2.533471E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.772 | TFLOPs: 42.79 | +7: iteration 7090/ 7508 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.57 | learning rate: 2.140E-05 | global batch size: 256 | lm loss: 2.557651E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.738 | TFLOPs: 42.59 | +7: iteration 7100/ 7508 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.57 | learning rate: 2.134E-05 | global batch size: 256 | lm loss: 2.518423E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.355 | TFLOPs: 42.75 | +7: iteration 7110/ 7508 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.58 | learning rate: 2.127E-05 | global batch size: 256 | lm loss: 2.577815E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.374 | TFLOPs: 42.27 | +7: iteration 7120/ 7508 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.56 | learning rate: 2.121E-05 | global batch size: 256 | lm loss: 2.539565E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.478 | TFLOPs: 43.62 | +7: iteration 7130/ 7508 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.57 | learning rate: 2.115E-05 | global batch size: 256 | lm loss: 2.561311E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.497 | TFLOPs: 42.47 | +7: iteration 7140/ 7508 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.58 | learning rate: 2.109E-05 | global batch size: 256 | lm loss: 2.539460E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.227 | TFLOPs: 42.16 | +7: iteration 7150/ 7508 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.58 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.547012E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.526 | TFLOPs: 42.19 | +7: iteration 7160/ 7508 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.58 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.572229E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.692 | TFLOPs: 42.40 | +7: iteration 7170/ 7508 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.58 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.574217E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.192 | TFLOPs: 42.06 | +7: iteration 7180/ 7508 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.58 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.555797E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.636 | TFLOPs: 41.91 | +7: iteration 7190/ 7508 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.57 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.527054E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.401 | TFLOPs: 42.94 | +7: iteration 7200/ 7508 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.58 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 2.535110E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.860 | TFLOPs: 42.03 | +7: iteration 7210/ 7508 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.58 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 2.550217E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.488 | TFLOPs: 42.38 | +7: iteration 7220/ 7508 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.59 | learning rate: 2.067E-05 | global batch size: 256 | lm loss: 2.545542E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 434.424 | TFLOPs: 41.42 | +7: iteration 7230/ 7508 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.58 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 2.556549E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 443.777 | TFLOPs: 42.31 | +7: iteration 7240/ 7508 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.56 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.565567E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 455.770 | TFLOPs: 43.45 | +7: iteration 7250/ 7508 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.58 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.577854E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.383 | TFLOPs: 41.99 | +7: iteration 7260/ 7508 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.58 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.523512E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 444.814 | TFLOPs: 42.41 | +7: iteration 7270/ 7508 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.57 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.564738E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 452.804 | TFLOPs: 43.17 | +7: iteration 7280/ 7508 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.58 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.570823E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.805 | TFLOPs: 41.93 | +7: iteration 7290/ 7508 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.58 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.557156E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.397 | TFLOPs: 41.99 | +7: iteration 7300/ 7508 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.62 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 2.566085E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 415.039 | TFLOPs: 39.57 | +7: iteration 7310/ 7508 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.58 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.553118E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 442.480 | TFLOPs: 42.19 | +7: iteration 7320/ 7508 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.56 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.539967E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 454.384 | TFLOPs: 43.32 | +7: iteration 7330/ 7508 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.57 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.555379E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.186 | TFLOPs: 42.54 | +7: iteration 7340/ 7508 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.58 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.524254E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 441.638 | TFLOPs: 42.11 | +7: iteration 7350/ 7508 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.57 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.545457E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.545 | TFLOPs: 42.67 | +7: iteration 7360/ 7508 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.59 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.562210E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 435.122 | TFLOPs: 41.48 | +7: iteration 7370/ 7508 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.57 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.543974E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 451.238 | TFLOPs: 43.02 | +7: iteration 7380/ 7508 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.57 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.548290E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 450.797 | TFLOPs: 42.98 | +7: iteration 7390/ 7508 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.60 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.517964E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 428.461 | TFLOPs: 40.85 | +7: iteration 7400/ 7508 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.56 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.557289E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.297 | TFLOPs: 43.60 | +7: iteration 7410/ 7508 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.58 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.563055E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 440.370 | TFLOPs: 41.98 | +7: iteration 7420/ 7508 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.57 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.514582E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.924 | TFLOPs: 42.61 | +7: iteration 7430/ 7508 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.57 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.544935E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 446.118 | TFLOPs: 42.53 | +7: iteration 7440/ 7508 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.57 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.495989E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.691 | TFLOPs: 42.49 | +7: iteration 7450/ 7508 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.58 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.544197E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 439.101 | TFLOPs: 41.86 | +7: iteration 7460/ 7508 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.57 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.556190E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.316 | TFLOPs: 42.74 | +7: iteration 7470/ 7508 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.57 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.520805E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 447.560 | TFLOPs: 42.67 | +7: iteration 7480/ 7508 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.57 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.519522E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 448.089 | TFLOPs: 42.72 | +7: iteration 7490/ 7508 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.56 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.552781E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 457.327 | TFLOPs: 43.60 | +7: iteration 7500/ 7508 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.57 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.513741E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 445.254 | TFLOPs: 42.45 | +0: [after training is done] datetime: 2022-11-25 19:00:49 +0: saving checkpoint at iteration 7508 to checkpoints_421m +7: ------------------------------------------------------------------------------------------------------------ +7: valid loss at the end of training for val data | lm loss value: 2.517285E+00 | lm loss PPL: 1.239490E+01 | +7: ------------------------------------------------------------------------------------------------------------ +0: [2022-11-25 19:00:49,194] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7508 is begin to save! +0: [2022-11-25 19:00:49,197] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_01-model_00-model_states.pt... +0: [2022-11-25 19:00:49,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_01-model_00-model_states.pt. +0: [2022-11-25 19:00:49,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_03-model_00-model_states.pt... +0: [2022-11-25 19:00:49,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_03-model_00-model_states.pt. +0: [2022-11-25 19:00:49,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_04-model_00-model_states.pt... +0: [2022-11-25 19:00:49,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_04-model_00-model_states.pt. +0: [2022-11-25 19:00:49,554] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_05-model_00-model_states.pt... +0: [2022-11-25 19:00:49,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_05-model_00-model_states.pt. +0: [2022-11-25 19:00:49,615] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_06-model_00-model_states.pt... +0: [2022-11-25 19:00:49,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_06-model_00-model_states.pt. +0: [2022-11-25 19:00:49,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_07-model_00-model_states.pt... +0: [2022-11-25 19:00:49,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_07-model_00-model_states.pt. +0: [2022-11-25 19:00:49,702] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_08-model_00-model_states.pt... +0: [2022-11-25 19:00:49,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_08-model_00-model_states.pt. +0: [2022-11-25 19:00:49,745] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_09-model_00-model_states.pt... +0: [2022-11-25 19:00:49,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_09-model_00-model_states.pt. +0: [2022-11-25 19:00:49,790] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_10-model_00-model_states.pt... +0: [2022-11-25 19:00:49,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_10-model_00-model_states.pt. +0: [2022-11-25 19:00:49,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_11-model_00-model_states.pt... +0: [2022-11-25 19:00:49,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_11-model_00-model_states.pt. +0: [2022-11-25 19:00:49,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_12-model_00-model_states.pt... +0: [2022-11-25 19:00:49,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_12-model_00-model_states.pt. +0: [2022-11-25 19:00:49,922] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_13-model_00-model_states.pt... +0: [2022-11-25 19:00:49,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_13-model_00-model_states.pt. +0: [2022-11-25 19:00:49,966] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_14-model_00-model_states.pt... +0: [2022-11-25 19:00:50,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_14-model_00-model_states.pt. +0: [2022-11-25 19:00:50,013] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_15-model_00-model_states.pt... +0: [2022-11-25 19:00:50,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_15-model_00-model_states.pt. +0: [2022-11-25 19:00:50,057] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_16-model_00-model_states.pt... +0: [2022-11-25 19:00:50,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_16-model_00-model_states.pt. +0: [2022-11-25 19:00:50,101] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_17-model_00-model_states.pt... +0: [2022-11-25 19:00:50,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_17-model_00-model_states.pt. +0: [2022-11-25 19:00:50,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_18-model_00-model_states.pt... +0: [2022-11-25 19:00:50,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_18-model_00-model_states.pt. +0: [2022-11-25 19:00:50,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_19-model_00-model_states.pt... +0: [2022-11-25 19:00:50,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_19-model_00-model_states.pt. +0: [2022-11-25 19:00:50,227] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_20-model_00-model_states.pt... +0: [2022-11-25 19:00:50,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_20-model_00-model_states.pt. +0: [2022-11-25 19:00:50,270] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/layer_22-model_00-model_states.pt... +0: [2022-11-25 19:00:50,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/layer_22-model_00-model_states.pt. +0: [2022-11-25 19:00:50,275] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_421m/global_step7508/mp_rank_00_model_states.pt +0: [2022-11-25 19:00:50,275] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/mp_rank_00_model_states.pt... +0: [2022-11-25 19:00:50,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/mp_rank_00_model_states.pt. +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +5: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2022-11-25 19:00:50,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_421m/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +3: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,388] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,389] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,389] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,390] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,393] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,394] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,395] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +5: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,396] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,397] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,398] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,399] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,400] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +6: [2022-11-25 19:00:50,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +6: [2022-11-25 19:00:50,401] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +6: [2022-11-25 19:00:50,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,402] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,403] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,404] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +5: [2022-11-25 19:00:50,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +5: [2022-11-25 19:00:50,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +4: [2022-11-25 19:00:50,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2022-11-25 19:00:50,408] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +4: [2022-11-25 19:00:50,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,410] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,407] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,392] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,405] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,405] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,406] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,413] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,413] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +2: [2022-11-25 19:00:50,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,414] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +2: [2022-11-25 19:00:50,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +2: [2022-11-25 19:00:50,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +1: [2022-11-25 19:00:50,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2022-11-25 19:00:50,416] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +1: [2022-11-25 19:00:50,416] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +3: [2022-11-25 19:00:50,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +3: [2022-11-25 19:00:50,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3: [2022-11-25 19:00:50,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2022-11-25 19:00:50,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,424] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +7: [2022-11-25 19:00:50,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +7: [2022-11-25 19:00:50,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2022-11-25 19:00:50,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: [2022-11-25 19:00:50,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_421m/global_step7508/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0: [2022-11-25 19:00:50,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7508 is ready now! +0: successfully saved checkpoint at iteration 7508 to checkpoints_421m +7: ------------------------------------------------------------------------------------------------------------ +7: test loss at the end of training for test data | lm loss value: 2.473832E+00 | lm loss PPL: 1.186784E+01 | +7: ------------------------------------------------------------------------------------------------------------ +END 2072596: Fri Nov 25 19:01:02 EET 2022 diff --git a/421m3b93b9/sbatch_421m.sh b/421m3b93b9/sbatch_421m.sh new file mode 100644 index 0000000000000000000000000000000000000000..10507f7bfd7a779c4ae05e738b8b50817a20d713 --- /dev/null +++ b/421m3b93b9/sbatch_421m.sh @@ -0,0 +1,160 @@ +#!/bin/bash +#SBATCH --nodes=8 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=256G +#SBATCH -p eap +#SBATCH -t 48:00:00 +#SBATCH --gpus-per-node=mi250:8 +#SBATCH --exclusive=user +#SBATCH --hint=nomultithread +#SBATCH --account=project_462000119 +#SBATCH -o logs/%j.out +#SBATCH -e logs/%j.err + +VARIANT=421m + +# if run without sbatch, invoke here +if [ -z $SLURM_JOB_ID ]; then + mkdir -p logs + sbatch "$0" + exit +fi + +set -euo pipefail + +# symlink logs/latest.out and logs/latest.err +ln -f -s $SLURM_JOB_ID.out logs/latest.out +ln -f -s $SLURM_JOB_ID.err logs/latest.err + +KILL_SWITCH_PATH=kill-switch-$VARIANT +CHECKPOINT_PATH=checkpoints_$VARIANT +TENSORBOARD_PATH=tensorboard_$VARIANT +# Start from scratch +rm -rf "$CHECKPOINT_PATH" "$TENSORBOARD_PATH" + +# Data +VOCAB_FILE="gpt2/vocab.json" +MERGE_FILE="gpt2/merges.txt" +DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document" + +PP_SIZE=1 +TP_SIZE=1 + +MICRO_BATCH_SIZE=4 +GRADIENT_ACCUMULATION_STEPS=1 +WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES)) +GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS)) + +# Model parameters +source model_params.sh +MODEL_PARAM=("${PARAM_425M[@]}") +NHIDDEN=${MODEL_PARAM[0]} +FFN_HIDDEN_SIZE=${MODEL_PARAM[1]} +KV_SIZE=${MODEL_PARAM[2]} +NHEADS=${MODEL_PARAM[3]} +NLAYERS=${MODEL_PARAM[4]} +SEQ_LEN=2048 + +echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS" + +SAVE_INTERVAL=1000 + +# Tokens: 3936562000 +# -> Samples: 1_922_149 +TRAIN_SAMPLES=1_922_149 + +OPTIMIZER_ARGS=" \ + --optimizer adam \ + --adam-beta1 0.9 \ + --adam-beta2 0.999 \ + --adam-eps 1e-8 \ + --lr 2e-4 \ + --min-lr 2e-5 \ + --lr-decay-style cosine \ + --lr-decay-samples $TRAIN_SAMPLES \ + --lr-warmup-samples 19_221 \ + --clip-grad 1.0 \ + --weight-decay 1e-1 \ + " + +GPT_ARGS=" \ + --num-layers $NLAYERS \ + --hidden-size $NHIDDEN \ + --num-attention-heads $NHEADS \ + --kv-channels $KV_SIZE \ + --ffn-hidden-size $FFN_HIDDEN_SIZE \ + --seq-length $SEQ_LEN \ + --max-position-embeddings $SEQ_LEN \ + --micro-batch-size $MICRO_BATCH_SIZE \ + --global-batch-size $GLOBAL_BATCH_SIZE \ + --train-samples $TRAIN_SAMPLES \ + --vocab-file $VOCAB_FILE \ + --merge-file $MERGE_FILE \ + --clip-grad 1.0 \ + --kill-switch-path $KILL_SWITCH_PATH \ + --bf16 \ + $OPTIMIZER_ARGS \ + " + +OUTPUT_ARGS=" \ + --log-interval 10 \ + --save-interval $SAVE_INTERVAL \ + --eval-interval 1000 \ + --eval-iters 1 \ + --tensorboard-dir $TENSORBOARD_PATH \ + --tensorboard-queue-size 5 \ + --log-timers-to-tensorboard \ + --log-batch-size-to-tensorboard \ + --log-validation-ppl-to-tensorboard \ + " + +ZERO_STAGE=0 + +mkdir -p ds_configs +DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json" + +cat < $DS_CONFIG_PATH +{ + "train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE, + "train_batch_size": $GLOBAL_BATCH_SIZE, + "gradient_clipping": 1.0, + "zero_optimization": { + "stage": $ZERO_STAGE + }, + "bf16": { + "enabled": true + }, + "steps_per_print": 2000, + "wall_clock_breakdown": false +} +EOF + +DEEPSPEED_ARGS=" \ + --deepspeed \ + --deepspeed_config $DS_CONFIG_PATH \ + --zero-stage $ZERO_STAGE \ + " + +CMD=" \ + Megatron-DeepSpeed/pretrain_gpt.py \ + --tensor-model-parallel-size $TP_SIZE \ + --pipeline-model-parallel-size $PP_SIZE \ + $GPT_ARGS \ + $OUTPUT_ARGS \ + --save $CHECKPOINT_PATH \ + --load $CHECKPOINT_PATH \ + --data-path $DATA_PATH \ + --data-impl mmap \ + --split 949,50,1 \ + $DEEPSPEED_ARGS \ + " + +echo $CMD + +echo "START $SLURM_JOBID: $(date)" + +# bash launch_srun.sh $CMD +srun --label launch.sh $CMD + +echo "END $SLURM_JOBID: $(date)" diff --git a/421m3b93b9/tensorboard/421m3b93b9pile/events.out.tfevents.1669391183.nid005099.47925.0 b/421m3b93b9/tensorboard/421m3b93b9pile/events.out.tfevents.1669391183.nid005099.47925.0 new file mode 100644 index 0000000000000000000000000000000000000000..0b8aef2f43baabc2627c082ac2a9ffeafe6be292 --- /dev/null +++ b/421m3b93b9/tensorboard/421m3b93b9pile/events.out.tfevents.1669391183.nid005099.47925.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128ad4997796243787d3115fe6259259e8f513e4789dfd68004ce65c6d54ad22 +size 13359407 diff --git a/421m3b93b9/tensorboard/lm1-421m-3b9-inv/2074233/events.out.tfevents.1669471433.nid005045.63499.0 b/421m3b93b9/tensorboard/lm1-421m-3b9-inv/2074233/events.out.tfevents.1669471433.nid005045.63499.0 new file mode 100644 index 0000000000000000000000000000000000000000..9169131d9c4f2f3fa0294ceb4117938d85351b36 --- /dev/null +++ b/421m3b93b9/tensorboard/lm1-421m-3b9-inv/2074233/events.out.tfevents.1669471433.nid005045.63499.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707f552f748ed83bda10904ff39aea42e266b910de12137752265fe262f0956d +size 13359721 diff --git a/421m3b93b9/transformers/config.json b/421m3b93b9/transformers/config.json new file mode 100644 index 0000000000000000000000000000000000000000..ea88768d351c626be3e9ca050a00f7a5eb7f522c --- /dev/null +++ b/421m3b93b9/transformers/config.json @@ -0,0 +1 @@ +{"vocab_size": 50304, "n_positions": 2048, "n_embd": 1280, "n_layer": 18, "n_head": 10, "n_inner": 5120, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"} \ No newline at end of file diff --git a/421m3b93b9/transformers/pytorch_model.bin b/421m3b93b9/transformers/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..f96aace76f0128e50129398e52675b9d3566006d --- /dev/null +++ b/421m3b93b9/transformers/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d191019ff34eb3d5ff9d29f2862d2dcd7500713276cf46caa4ef1752381303b +size 993488781